© 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. 129793
    Prev
    Next
    INDEX
    Explanations

    Common tokens

    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
    :variables
    -0.30
    isclosed
    -0.29
    å¼Ĥåij³
    -0.26
    acha
    -0.25
    ólogo
    -0.25
    èĩ³ä¸Ĭ
    -0.24
     sidelines
    -0.24
    rolls
    -0.24
    ISCO
    -0.24
    NetMessage
    -0.24
    POSITIVE LOGITS
    è½½
    0.31
     rel
    0.28
     lean
    0.28
    仪
    0.25
     adding
    0.25
     rif
    0.25
     ent
    0.25
     domin
    0.24
     Desc
    0.24
    åĪij
    0.24
    Activations Density 0.002%

    No Known Activations