© 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. 24334
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    avor
    -0.27
     *)"
    -0.26
    isans
    -0.25
    plr
    -0.25
    åĨįåİ»
    -0.25
    uzzi
    -0.24
    çļĦè¦ģæ±Ĥ
    -0.23
    бол
    -0.23
    .mobile
    -0.23
     Bundesliga
    -0.23
    POSITIVE LOGITS
    Yes
    0.30
     Jud
    0.30
    ç¥Ŀ
    0.29
    Nice
    0.27
     glad
    0.27
    .mount
    0.27
    Thank
    0.27
    害
    0.26
    jem
    0.26
     Reply
    0.26
    Activations Density 0.038%

    No Known Activations