© 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. 25-TRANSCODER-HP
    7. 107911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç§ģ
    -0.25
     *__
    -0.25
     ksz
    -0.25
    saving
    -0.25
    ä»ĸèĩªå·±
    -0.25
    omin
    -0.25
    åŃĺåľ¨äºİ
    -0.25
     norske
    -0.24
    -Star
    -0.24
    ontology
    -0.23
    POSITIVE LOGITS
    çĺ¤
    0.29
     expected
    0.27
    opp
    0.26
    less
    0.25
    ikh
    0.25
     depth
    0.25
     captured
    0.24
    à¹ĭ
    0.24
    oj
    0.24
     exposed
    0.24
    Activations Density 0.916%

    No Known Activations

    This feature has no known activations.