© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25896
    Prev
    Next
    INDEX
    Explanations

    expecting

    np_max-act · gemini-2.0-flash

    mentions of pregnancy or an expected/actual childbirth (people expecting or having a child).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icious
    -0.08
    HOLDER
    -0.07
     благодар
    -0.07
     complains
    -0.07
     grim
    -0.07
     MAS
    -0.07
    _GOOD
    -0.06
     تو
    -0.06
     Prometheus
    -0.06
    (des
    -0.06
    POSITIVE LOGITS
    ')">
    0.09
     ");
    0.08
    ！");↵
    0.08
    :\"
    0.08
    מניות
    0.08
    道士职业
    0.08
    法师职业
    0.07
    rary
    0.07
    хож
    0.07
    <?↵
    0.07
    Activations Density 0.025%

    No Known Activations