© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162981
    Prev
    Next
    INDEX
    Explanations

    tropical and temperate climates

    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
    æľĢè¿ij
    -0.26
     Äijá»Ŀi
    -0.26
    hare
    -0.26
    箸
    -0.25
    sit
    -0.25
    /code
    -0.25
    relative
    -0.24
    recent
    -0.24
    spar
    -0.23
    -os
    -0.23
    POSITIVE LOGITS
    ity
    0.31
    温
    0.27
    åı¶
    0.26
    geb
    0.26
    ีย
    0.25
    __(*
    0.25
    velt
    0.25
    ãĥĭãĥ¼
    0.25
    .Dataset
    0.25
     subt
    0.25
    Activations Density 0.016%

    No Known Activations