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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163224
    Prev
    Next
    INDEX
    Explanations

    of

    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
    RCT
    -0.26
    бол
    -0.26
    ĥģ
    -0.25
    mát
    -0.24
    (des
    -0.24
    SDL
    -0.23
    裱
    -0.23
    ading
    -0.23
    acon
    -0.23
    ToMany
    -0.22
    POSITIVE LOGITS
    åIJĦèĩª
    0.29
    anness
    0.29
    åIJĦç§į
    0.28
     behaves
    0.27
    ä¸¤åľ°
    0.27
    æĬĺ
    0.26
    è¡Į为
    0.26
    ä¸įåIJĮ
    0.26
     behaving
    0.25
     behaved
    0.25
    Activations Density 0.001%

    No Known Activations