© 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. 24-TRANSCODER-HP
    7. 149871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confronting
    -0.26
    è¯ķè¡Į
    -0.25
    æŃ¥æŃ¥
    -0.25
     campus
    -0.25
    _hid
    -0.24
    -campus
    -0.24
    ffb
    -0.24
    棱
    -0.23
    servername
    -0.23
     gamm
    -0.23
    POSITIVE LOGITS
    anje
    0.27
    ç»Ħç»ĩé¢Ĩ导
    0.25
    ling
    0.25
    _
    0.24
    ournal
    0.24
    rement
    0.23
    ead
    0.23
    æŶéĹ´æ®µ
    0.23
     Zug
    0.23
    eson
    0.23
    Activations Density 0.078%

    No Known Activations

    This feature has no known activations.