© 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. 32-TRANSCODER-HP
    7. 42456
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ«å¤§
    -0.32
    plets
    -0.31
     teaspoons
    -0.25
    -pills
    -0.25
    æĪijåıªæĺ¯
    -0.24
    éģĵ
    -0.24
    Restore
    -0.24
    indr
    -0.24
    aurus
    -0.24
    itive
    -0.24
    POSITIVE LOGITS
    Meet
    0.28
    ek
    0.27
    uu
    0.27
    fm
    0.26
    uty
    0.26
     meet
    0.26
    meet
    0.26
    _flip
    0.26
    anton
    0.25
    ubb
    0.25
    Activations Density 0.004%

    No Known Activations