© 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. 98206
    Prev
    Next
    INDEX
    Explanations

    code/technical content

    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
    ecz
    -0.27
    :?
    -0.24
    ICS
    -0.23
    ’
    -0.23
    缮
    -0.23
    å®Ī
    -0.23
    ä½İ
    -0.22
    åŃĹ
    -0.22
    %'↵
    -0.22
    HCI
    -0.22
    POSITIVE LOGITS
    omo
    0.26
    _BO
    0.25
    ãģ¤ãģĦ
    0.25
    Bear
    0.24
    mary
    0.24
     Bros
    0.23
    çĻ½èī²çļĦ
    0.23
     behand
    0.22
    [Unit
    0.22
    èµ°äºĨ
    0.22
    Activations Density 0.003%

    No Known Activations