© 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. 17302
    Prev
    Next
    INDEX
    Explanations

    1 2 8 0 } / Top material

    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
    andle
    -0.09
    iset
    -0.09
    éĦĦ
    -0.09
     Blanco
    -0.09
    åģ¥åº·çļĦ
    -0.08
    ä¸ĭæ²ī
    -0.08
    .Theme
    -0.08
    _HAL
    -0.08
    äºĽè®¸
    -0.08
    acco
    -0.08
    POSITIVE LOGITS
    åı¦æľī
    0.09
    Æ°u
    0.09
    odor
    0.08
    å¿ĥçģµ
    0.08
    ỵ
    0.08
    plural
    0.08
    trer
    0.08
    vron
    0.08
    _plural
    0.08
    lector
    0.08
    Activations Density 0.030%

    No Known Activations