© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129559
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roat
    -0.28
    AdapterFactory
    -0.26
    ierz
    -0.25
    责令
    -0.25
     nominee
    -0.24
    .full
    -0.23
    JOB
    -0.23
     shall
    -0.23
     SHALL
    -0.23
    é¨İ
    -0.23
    POSITIVE LOGITS
    ldata
    0.26
    äºĨå¤ļå°ij
    0.26
    ä¸įåı¯èĥ½
    0.26
    æľªå¿ħ
    0.25
    åµĺ
    0.25
     Previously
    0.25
    .mass
    0.25
    oler
    0.25
    ç¥Ł
    0.25
    unlikely
    0.25
    Activations Density 0.003%

    No Known Activations