© 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. 162440
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    highest
    -0.28
    åº
    -0.28
     highest
    -0.25
    mdb
    -0.24
    icals
    -0.24
    quette
    -0.24
     root
    -0.24
    æł¹
    -0.23
    ç»ıå¼Ģ
    -0.23
     practical
    -0.23
    POSITIVE LOGITS
    ä¸Ģå¤ľ
    0.30
    clair
    0.26
    boy
    0.26
     trajectories
    0.25
    æĻļæľŁ
    0.25
    "bytes
    0.24
    轨迹
    0.24
     Eisen
    0.23
    ç£Ķ
    0.23
    _mar
    0.23
    Activations Density 0.006%

    No Known Activations