© 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. 162460
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     lastIndex
    -0.28
     Introduced
    -0.25
    _frequency
    -0.25
     Presented
    -0.25
    çĶļèĩ³
    -0.25
    hana
    -0.24
    Choices
    -0.24
    -frequency
    -0.24
     chem
    -0.24
    çĩĥ
    -0.24
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.29
    çĿ¡çľł
    0.29
    è´¡çĮ®
    0.28
    æľ¬èº«
    0.27
    OOT
    0.27
    书ä¸Ń
    0.26
    åIJĦæł·
    0.25
    沧æ¡ij
    0.25
    ONGL
    0.25
     Camp
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.