© 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. 162577
    Prev
    Next
    INDEX
    Explanations

    use

    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
     nonetheless
    -0.28
    åĨµä¸Ķ
    -0.25
     cancell
    -0.25
    ä¼ļè§ģ
    -0.25
     novitÃł
    -0.24
    swap
    -0.24
    ä¸įéĶĻ
    -0.23
    足
    -0.23
    æĭħ
    -0.23
    è¿ĺéľĢè¦ģ
    -0.23
    POSITIVE LOGITS
     Expect
    0.27
    ÑĻ
    0.27
    Expect
    0.27
    (limit
    0.26
     pot
    0.25
    /original
    0.25
    ики
    0.25
     lim
    0.24
     expectation
    0.24
    OUT
    0.24
    Activations Density 0.003%

    No Known Activations