© 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. 19-RESID-POST-AA
    6. 75549
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    aits
    -0.07
    ㎰
    -0.07
     davran
    -0.07
     reefs
    -0.07
    afe
    -0.06
     Sections
    -0.06
    켙
    -0.06
     dex
    -0.06
     Dubai
    -0.06
    계
    -0.06
    POSITIVE LOGITS
    (move
    0.08
    ジー
    0.07
    帳
    0.07
     Making
    0.07
    全是
    0.07
     literally
    0.07
    .showMessage
    0.07
    wishlist
    0.07
     hide
    0.07
    _=
    0.07
    Activations Density 0.006%

    No Known Activations