© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18417
    Prev
    Next
    INDEX
    Explanations

    pencil, stencil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iegel
    -0.09
    ubble
    -0.09
    ies
    -0.08
    ILITY
    -0.08
    /off
    -0.08
    olic
    -0.08
    ustin
    -0.08
    _endian
    -0.08
    olu
    -0.08
    ensitivity
    -0.08
    POSITIVE LOGITS
    rose
    0.11
    棹
    0.10
    å±ij
    0.10
    ç¬ı
    0.10
    æ±Łå±±
    0.09
    warm
    0.09
    å¦Ī
    0.09
    黼
    0.09
    太快
    0.09
    åģķ
    0.09
    Activations Density 0.005%

    No Known Activations