© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 5953
    Prev
    Next
    INDEX
    Explanations

    say "pl words"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     REL
    -0.07
    噴
    -0.07
    ifies
    -0.07
     farklı
    -0.07
    тся
    -0.07
     decorate
    -0.06
    坯
    -0.06
    .Xr
    -0.06
    (TEXT
    -0.06
     cómo
    -0.06
    POSITIVE LOGITS
     Maur
    0.08
    ↵
    ↵
    ↵
    0.07
    中最
    0.07
    溲
    0.07
    卖场
    0.07
     ransom
    0.07
    ユー�
    0.07
    	bus
    0.07
     componentDidUpdate
    0.07
    专场
    0.07
    Activations Density 0.000%

    No Known Activations