© 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. 69426
    Prev
    Next
    INDEX
    Explanations

    0

    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
     ccp
    -0.07
    дол
    -0.07
     councillors
    -0.07
    _ipv
    -0.07
    _sec
    -0.07
    "url
    -0.07
     Apr
    -0.07
    crop
    -0.06
     ranking
    -0.06
    捕鱼
    -0.06
    POSITIVE LOGITS
     ART
    0.08
     كلم
    0.08
     театр
    0.07
     withdraw
    0.07
    いれば
    0.07
     BANK
    0.07
     example
    0.07
     resident
    0.07
    として
    0.06
     Picasso
    0.06
    Activations Density 0.002%

    No Known Activations