© 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. 150528
    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
    gmail
    -0.28
    ìĦ¤
    -0.25
    unar
    -0.24
    è¿©
    -0.24
    ByPrimaryKey
    -0.24
     oppos
    -0.24
    ibel
    -0.24
     íķŃ
    -0.24
    à¹īาà¸ĩ
    -0.24
    å¾®åķĨ
    -0.23
    POSITIVE LOGITS
     Guth
    0.29
    æĶĺ
    0.27
    临æŶ
    0.26
    èķ¤
    0.24
    离
    0.24
    Temporary
    0.24
    解éĩĬ
    0.24
     currentState
    0.23
    itation
    0.23
     Malta
    0.23
    Activations Density 0.934%

    No Known Activations

    This feature has no known activations.