© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    uk place names

    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
    /maps
    -0.09
    pend
    -0.09
    umpt
    -0.09
    olute
    -0.08
    æĹĮ
    -0.08
    eton
    -0.08
    讲
    -0.08
    usch
    -0.07
    igit
    -0.07
    ../../../
    -0.07
    POSITIVE LOGITS
    alm
    0.12
    ãģ¤ãģĭ
    0.10
    iveness
    0.10
    lops
    0.10
    TAIL
    0.10
    å·´å·´
    0.10
    aim
    0.10
    loh
    0.10
    side
    0.09
    Beans
    0.09
    Activations Density 0.002%

    No Known Activations