© 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. 150137
    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
     cy
    -0.30
     painting
    -0.29
     having
    -0.27
     overs
    -0.27
     maneuvers
    -0.27
    ç³ľ
    -0.26
    ÑģÑĤавил
    -0.26
     pouring
    -0.26
     already
    -0.26
     putting
    -0.25
    POSITIVE LOGITS
    ä¹ĭåŁİ
    0.30
    lish
    0.27
     çı
    0.26
    axon
    0.26
    _AUD
    0.26
    async
    0.25
    allis
    0.25
    æĥħä¾£
    0.25
    ç¼ĵ
    0.25
    aud
    0.25
    Activations Density 0.156%

    No Known Activations

    This feature has no known activations.