© 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. 112174
    Prev
    Next
    INDEX
    Explanations

    technical/formal language

    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
    ä¸įåĪĨ
    -0.26
    /slider
    -0.24
    оÑģÑĤи
    -0.24
    egal
    -0.23
    ctal
    -0.23
    MED
    -0.23
    .experimental
    -0.23
    aca
    -0.23
    .fix
    -0.23
    ç±³é¥Ń
    -0.23
    POSITIVE LOGITS
     eff
    0.27
    循
    0.25
     dirs
    0.24
     wrought
    0.23
    bane
    0.23
    æľīæķĪæĢ§
    0.23
    éĩĬ
    0.23
     men
    0.23
    -issue
    0.22
    稳å®ļæĢ§
    0.22
    Activations Density 0.052%

    No Known Activations