© 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. 162359
    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
    .sap
    -0.32
    _upgrade
    -0.27
    èģĶ
    -0.27
    åįĩ温
    -0.25
    layer
    -0.25
     belong
    -0.24
    çį¨
    -0.24
    æĬĬ她
    -0.24
    .ser
    -0.24
    utra
    -0.24
    POSITIVE LOGITS
     picnic
    0.26
    èĴĭä»ĭçŁ³
    0.25
    hood
    0.24
    oodle
    0.23
     trib
    0.23
    xon
    0.23
    马åĬĽ
    0.23
    irez
    0.23
    Č↵
    0.23
    exual
    0.23
    Activations Density 0.190%

    No Known Activations

    This feature has no known activations.