© 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. 24607
    Prev
    Next
    INDEX
    Explanations

    Source information

    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
    rive
    -0.31
    ramids
    -0.25
    ','=
    -0.25
     dÆ°Æ¡ng
    -0.25
    ecycle
    -0.25
    fühl
    -0.24
     Provid
    -0.24
    âĻ©
    -0.24
    nonnull
    -0.24
    äºļ马
    -0.23
    POSITIVE LOGITS
    ç¼ĸè¾ij
    0.28
     Author
    0.28
    稿
    0.27
    [^
    0.26
    æľ¬æĸĩ
    0.26
    éĿĪ
    0.25
     @
    0.25
     editor
    0.25
     Station
    0.24
     #
    0.24
    Activations Density 0.027%

    No Known Activations