Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5622
    Prev
    Next
    INDEX
    Explanations

    inhibition

    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
     Bowie
    -0.07
     Passage
    -0.07
    ADS
    -0.07
     },↵↵↵
    -0.07
    oulos
    -0.07
    _CF
    -0.06
     dv
    -0.06
    起身
    -0.06
    ">
    ↵
    ↵
    -0.06
    casts
    -0.06
    POSITIVE LOGITS
    狀況
    0.07
    ят
    0.07
     inhibition
    0.07
    扼
    0.07
    categoryId
    0.07
    אמת
    0.07
    :error
    0.07
     notorious
    0.06
    社会保障
    0.06
    .setStroke
    0.06
    Activations Density 0.016%

    No Known Activations