© 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. 150915
    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
    ainers
    -0.27
    erais
    -0.26
    ayscale
    -0.26
    ä½ĵç³»
    -0.25
    åŁ¹
    -0.25
    è§īæĤŁ
    -0.24
    bru
    -0.24
    è¡Įç¨ĭ
    -0.24
    é¢ĨåŁŁ
    -0.23
    phas
    -0.23
    POSITIVE LOGITS
    osed
    0.27
    rü
    0.26
    effect
    0.25
    æĹłè¾ľ
    0.24
    ÑĤол
    0.23
    鸽
    0.23
    ocate
    0.23
    _story
    0.23
     svenska
    0.23
    è¾ŀ
    0.23
    Activations Density 0.120%

    No Known Activations

    This feature has no known activations.