© 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. 112755
    Prev
    Next
    INDEX
    Explanations

    passed

    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
    mol
    -0.28
     mol
    -0.26
    èĥ¶
    -0.25
    ç»ıçIJĨ
    -0.25
     Vlad
    -0.25
    ä¼ĹæīĢåij¨çŁ¥
    -0.25
    ogui
    -0.24
     Concept
    -0.24
    åĪ¶
    -0.24
    .forChild
    -0.24
    POSITIVE LOGITS
    edException
    0.29
    lias
    0.26
     stal
    0.24
    elay
    0.23
     datatable
    0.23
    sticks
    0.22
    deep
    0.22
    ,application
    0.22
    ordinate
    0.22
    osos
    0.22
    Activations Density 0.001%

    No Known Activations