© 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. 97542
    Prev
    Next
    INDEX
    Explanations

    code/documentation config

    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
    unbind
    -0.28
    å·§åħĭåĬĽ
    -0.27
    iren
    -0.26
    æ»ĵ
    -0.26
    ansa
    -0.26
    _BINDING
    -0.25
    æ§Ľ
    -0.24
     yaptır
    -0.24
    cheid
    -0.24
    conti
    -0.24
    POSITIVE LOGITS
     Min
    0.31
    çĽĺ
    0.30
     Far
    0.28
     Be
    0.27
     http
    0.26
    лаг
    0.26
     Set
    0.26
     BY
    0.26
     Kids
    0.26
    缤
    0.25
    Activations Density 0.009%

    No Known Activations