© 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. 23268
    Prev
    Next
    INDEX
    Explanations

    a or an before a word

    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
    aget
    -0.11
    feit
    -0.09
    æīĥ
    -0.08
     minimal
    -0.08
    urdy
    -0.08
     polo
    -0.08
    åħīéĺ´
    -0.08
    ä¸ºä½ł
    -0.08
    _sid
    -0.08
     Dzi
    -0.08
    POSITIVE LOGITS
    åħļåijĺ
    0.10
    oba
    0.10
    8
    0.10
    4
    0.09
    9
    0.09
    6
    0.09
     cặp
    0.09
    åħ¨ç¤¾ä¼ļ
    0.09
    7
    0.09
    3
    0.09
    Activations Density 0.079%

    No Known Activations