© 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. 15-RESID-POST-AA
    6. 26400
    Prev
    Next
    INDEX
    Explanations

    fix

    np_max-act · gemini-2.0-flash
    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
    pé
    -0.09
     sollte
    -0.07
    lopedia
    -0.07
     simplement
    -0.07
    anine
    -0.07
    Ẳ
    -0.07
     setContent
    -0.07
     comentário
    -0.07
     sprint
    -0.07
     UIAlertAction
    -0.07
    POSITIVE LOGITS
    ervers
    0.07
     spells
    0.07
     cortical
    0.07
    旭
    0.06
     forts
    0.06
    .dto
    0.06
    \t
    0.06
    宝贝
    0.06
    >${
    0.06
    вшис
    0.06
    Activations Density 0.035%

    No Known Activations