© 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. 19-RESID-POST-AA
    11. 8298
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     الترك
    -0.07
     neglected
    -0.07
    -inc
    -0.07
     primes
    -0.07
     DataSource
    -0.07
     Điểm
    -0.07
    _paint
    -0.07
    投注
    -0.06
     Lust
    -0.06
     Feedback
    -0.06
    POSITIVE LOGITS
    板
    0.08
     '',
    0.07
    אוטומ
    0.07
    閉
    0.06
    small
    0.06
    RT
    0.06
     systemctl
    0.06
     guy
    0.06
     yetiştir
    0.06
    朋友们
    0.06
    Activations Density 0.000%

    No Known Activations