© 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. 163803
    Prev
    Next
    INDEX
    Explanations

    addition

    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
    owler
    -0.28
    ateur
    -0.28
    ivos
    -0.27
    ainer
    -0.26
    度
    -0.25
    æµ®
    -0.25
     Cutter
    -0.25
    ierce
    -0.25
    积
    -0.25
    otive
    -0.25
    POSITIVE LOGITS
    æѤå¤ĸ
    0.30
    ä¸įä»ħå¦ĤæѤ
    0.30
    ä¹ĭå¤ĸ
    0.29
     Additionally
    0.29
     additionally
    0.29
     besides
    0.28
    Additionally
    0.28
    éħįæľī
    0.28
    ä»ĸè¿ĺ
    0.27
     Cl
    0.27
    Activations Density 0.025%

    No Known Activations