© 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. 149993
    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
    _inst
    -0.25
    pron
    -0.25
    Leader
    -0.25
    ä¾Ľåħ»
    -0.25
    macros
    -0.25
     strapped
    -0.24
     пиÑĤ
    -0.24
     leaders
    -0.24
    åŁºæľ¬ä¿¡æģ¯
    -0.24
    	inst
    -0.24
    POSITIVE LOGITS
     style
    0.27
    个æĢ§
    0.26
    eil
    0.26
    coding
    0.25
    avirus
    0.24
    严èĤĥ
    0.24
    èĩªåĬ©
    0.24
    ç«ĭæ¡Ī
    0.23
    codigo
    0.23
    æĪ¿ç§Ł
    0.23
    Activations Density 1.299%

    No Known Activations

    This feature has no known activations.