© 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. 162447
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
    ãģ®ãģ§
    -0.49
    人éĥ½
    -0.33
    ãģĦãģ¾ãģĻ
    -0.30
    ãģĦãģŁ
    -0.28
    izedName
    -0.27
    licity
    -0.26
    èĩ¾
    -0.25
    hton
    -0.23
    -thirds
    -0.23
    ä¹İ
    -0.23
    POSITIVE LOGITS
    s
    1.74
    sheets
    0.77
    sar
    0.72
    sampling
    0.67
    sand
    0.67
    sist
    0.66
    squ
    0.63
    sie
    0.62
    suit
    0.62
    sus
    0.61
    Activations Density 0.233%

    No Known Activations