© 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. 129834
    Prev
    Next
    INDEX
    Explanations

    General informative text

    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
    èĪįå¾Ĺ
    -0.26
    rs
    -0.24
    ereg
    -0.23
     sourcing
    -0.23
     Same
    -0.23
    _summary
    -0.23
     house
    -0.23
     tá»ī
    -0.23
    æĵį
    -0.22
    ubre
    -0.22
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.35
    ä¸Ĭå¸Ĥ
    0.34
     successful
    0.31
    èħ©
    0.31
     winning
    0.30
     winner
    0.29
     winners
    0.29
    诺è´Ŀå°Ķ
    0.29
    çĶŁæķĪ
    0.29
    çĻ»ä¸Ĭ
    0.28
    Activations Density 0.013%

    No Known Activations