© 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. 24681
    Prev
    Next
    INDEX
    Explanations

    series/product part, version

    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
    éré
    -0.27
     bä
    -0.26
    械
    -0.25
     dep
    -0.24
    -grow
    -0.23
     bpp
    -0.23
    çļĦå¢ŀéķ¿
    -0.23
    cona
    -0.23
     RATE
    -0.23
    æĿIJ
    -0.23
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.30
     Harding
    0.26
     part
    0.26
    åĿĽ
    0.25
    nees
    0.25
    ãģ£ãģįãĤĬ
    0.25
    chef
    0.25
    usher
    0.25
    éĤ£æ®µ
    0.25
    ).'
    0.24
    Activations Density 0.022%

    No Known Activations