© 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. 27-TRANSCODER-HP
    7. 57741
    Prev
    Next
    INDEX
    Explanations

    catabolism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptr
    -0.26
     trustees
    -0.24
    æľĿ
    -0.24
    lig
    -0.24
     convoy
    -0.24
     oversight
    -0.23
     enlightened
    -0.23
     allocations
    -0.23
    '\
    -0.23
    IDD
    -0.23
    POSITIVE LOGITS
    ä¼ĹæīĢ
    0.31
    anon
    0.29
    ä¸İåıijå±ķ
    0.27
    éģĵ
    0.27
    son
    0.26
     Teh
    0.25
    illary
    0.25
    ìĨIJ
    0.25
     futures
    0.25
    åĹij
    0.25
    Activations Density 0.034%

    No Known Activations