© 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. 163421
    Prev
    Next
    INDEX
    Explanations

    Code and data structures

    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
     associates
    -0.28
    对åºĶ
    -0.26
    ä»ĭç»įäºĨ
    -0.25
     builds
    -0.25
    omap
    -0.24
    对æѤ
    -0.24
     ripple
    -0.23
    éģģ
    -0.23
     bubble
    -0.23
     associate
    -0.23
    POSITIVE LOGITS
     typeof
    0.34
    ä¸Ńå¿ĥ主任
    0.32
    typeof
    0.31
    主导
    0.29
    andler
    0.28
    idor
    0.28
    aminer
    0.28
    <typeof
    0.28
    .GetType
    0.26
    SmartPointer
    0.26
    Activations Density 0.014%

    No Known Activations