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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 7911
    Prev
    Next
    INDEX
    Explanations

    say "the ending -er"

    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
    .coroutines
    -0.07
     autonomy
    -0.07
     violence
    -0.07
    包围
    -0.07
     enlargement
    -0.07
     '=
    -0.07
    酾
    -0.07
    的精神
    -0.07
    唠
    -0.07
    绿色发展
    -0.07
    POSITIVE LOGITS
    Wei
    0.07
     Escort
    0.07
    למת
    0.07
    Press
    0.07
     Yankee
    0.07
     ko
    0.07
    Hold
    0.07
     STA
    0.06
    Ҫ
    0.06
    ינג
    0.06
    Activations Density 0.130%

    No Known Activations