© 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
    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. 89761
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ☬
    -0.08
     Lal
    -0.07
     lambda
    -0.07
    upyter
    -0.07
     Tac
    -0.07
     Dann
    -0.07
    谈话
    -0.07
    rikes
    -0.06
    Plug
    -0.06
    conda
    -0.06
    POSITIVE LOGITS
    目前为止
    0.08
    サポート
    0.07
     męsk
    0.07
    继续保持
    0.07
    ㎏
    0.07
     stab
    0.07
    🇪
    0.06
    韓
    0.06
     SC
    0.06
    Manchester
    0.06
    Activations Density 0.001%

    No Known Activations