© 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. 61720
    Prev
    Next
    INDEX
    Explanations

    nearby + locations

    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
    pile
    -0.09
     dabei
    -0.09
    ufe
    -0.09
    aceous
    -0.09
     СШÐIJ
    -0.09
    arily
    -0.09
    ä¸Ĭçľĭ
    -0.09
    è¿ĽéŨ
    -0.09
    backs
    -0.08
    /ph
    -0.08
    POSITIVE LOGITS
    ä¸įè¿ľå¤Ħ
    0.13
    ness
    0.11
    hood
    0.11
    abouts
    0.10
    shore
    0.10
    NESS
    0.09
     Äijâu
    0.09
    té
    0.09
    ood
    0.09
    /on
    0.09
    Activations Density 0.006%

    No Known Activations