© 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. 98697
    Prev
    Next
    INDEX
    Explanations

    Location/position

    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
     Rath
    -0.27
    ải
    -0.24
    ınd
    -0.24
    ocrin
    -0.24
    ẫ
    -0.23
    rich
    -0.23
    aco
    -0.23
    eli
    -0.23
     SOUR
    -0.23
    åľĨå½¢
    -0.23
    POSITIVE LOGITS
     terminator
    0.29
    ional
    0.27
    AGMA
    0.26
     primaries
    0.25
     embr
    0.25
    _PRIMARY
    0.24
    __[
    0.24
     hung
    0.23
    é¼İ
    0.23
    SENT
    0.23
    Activations Density 0.010%

    No Known Activations