© 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. 23-TRANSCODER-HP
    7. 24803
    Prev
    Next
    INDEX
    Explanations

    medical/scientific articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possible
    -0.30
    atable
    -0.30
    thon
    -0.29
     Harbor
    -0.28
    inion
    -0.28
    possible
    -0.27
     posible
    -0.27
     gen
    -0.25
    ansion
    -0.25
    cmath
    -0.24
    POSITIVE LOGITS
    å¤±çľł
    0.31
    æłĹ
    0.31
    头æĻķ
    0.30
    è¿ŁåĪ°
    0.30
    TypeName
    0.29
    åĹĵåŃIJ
    0.29
    rances
    0.29
    失ä¸ļ
    0.28
    éģ
    0.28
    乱象
    0.28
    Activations Density 0.014%

    No Known Activations