© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24712
    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
    ä»»ä½ķ人
    -0.27
     ITE
    -0.26
    çĪ¸å¦Ī
    -0.25
    å½ĵå±Ģ
    -0.25
    缤
    -0.25
    女åħĴ
    -0.25
    _EQUALS
    -0.24
    ä»İåݻ年
    -0.24
    à²ł
    -0.24
    DATABASE
    -0.24
    POSITIVE LOGITS
    广
    0.28
    ARC
    0.28
    -house
    0.27
    åĬ¿
    0.26
    rug
    0.26
    è¿Ľåı£
    0.26
    ARA
    0.26
     Higgins
    0.26
    追
    0.25
    oola
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.