© 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. 162311
    Prev
    Next
    INDEX
    Explanations

    with

    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
    æĶ¾å¿ĥ
    -0.30
    è£ģ
    -0.28
    éĢļè¡Įè¯ģ
    -0.27
    诸
    -0.25
    窿
    -0.25
    atal
    -0.25
    è´¸
    -0.24
    åIJİåĭ¤
    -0.24
    ä¸įå¿ħ
    -0.24
    rypton
    -0.23
    POSITIVE LOGITS
    æľī没æľī
    0.26
    .shtml
    0.25
     expectedResult
    0.25
    .Offset
    0.25
    .native
    0.25
    obox
    0.24
    该åİ¿
    0.24
     Offset
    0.24
     GRAPH
    0.24
    mention
    0.24
    Activations Density 0.004%

    No Known Activations