© 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. 162437
    Prev
    Next
    INDEX
    Explanations

    Code and copyright notices

    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
    çļĦæĦŁåıĹ
    -0.28
    substr
    -0.27
    çļĦæĦŁè§ī
    -0.25
    nameof
    -0.25
    çļĦèĥ½åĬĽ
    -0.25
    åIJİæİĴ
    -0.25
    åŁĭ
    -0.24
    è²Ĥ
    -0.24
    gene
    -0.24
     Columbus
    -0.24
    POSITIVE LOGITS
     liá»ĩu
    0.26
    lla
    0.25
    iko
    0.24
    åħ¬æĬ¥
    0.24
    atts
    0.24
    áºŃy
    0.24
    ISTA
    0.24
    erva
    0.24
    æĬ¥åijĬ
    0.23
    ACH
    0.23
    Activations Density 0.022%

    No Known Activations