© 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. 163802
    Prev
    Next
    INDEX
    Explanations

    descriptive language

    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
    ä½Ļ
    -0.29
    advance
    -0.27
    ä½Ļ家
    -0.26
    辫
    -0.26
    为ä¹ĭ
    -0.26
    ilik
    -0.25
    åĨįè§ģ
    -0.25
     Advance
    -0.25
    remain
    -0.24
     Lehr
    -0.24
    POSITIVE LOGITS
     because
    0.36
    åĽłä¸ºä»ĸ们
    0.33
     whereas
    0.33
    åĽłä¸ºæĪij们
    0.31
    eren
    0.30
    izer
    0.30
    åĽłä¸º
    0.29
    åĽłä¸ºæĪij
    0.29
    åĽłä¸ºå®ĥ
    0.28
    åĽłä¸ºåľ¨
    0.28
    Activations Density 0.009%

    No Known Activations