© 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. 162630
    Prev
    Next
    INDEX
    Explanations

    Conversational / Question-related texts

    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
    oder
    -0.28
     geme
    -0.27
     partial
    -0.26
     nonzero
    -0.26
    avo
    -0.26
    éĢ®
    -0.26
    æĪĸå¤ļæĪĸå°ij
    -0.25
    ä¸įåIJĮç¨ĭ度
    -0.25
    åŃ³
    -0.25
     Gas
    -0.25
    POSITIVE LOGITS
    æĺ¯æ²¡æľī
    0.26
    upt
    0.26
    就没æľī
    0.25
    没äºĨ
    0.25
    æĺ¯ä»Ģä¹Īåij¢
    0.25
    qv
    0.25
     exclusively
    0.24
     lack
    0.24
    åħ»èĢģæľįåĬ¡
    0.24
    ymb
    0.24
    Activations Density 0.003%

    No Known Activations