© 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. 49879
    Prev
    Next
    INDEX
    Explanations

    walker, bush, arena

    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
    imen
    -0.10
    ä¸ĭå·´
    -0.09
    çĦ¶æĺ¯
    -0.09
    pons
    -0.09
    æ¥Ķ
    -0.09
     Toe
    -0.08
    ãģĭãģ¤
    -0.08
    _AUX
    -0.08
    ãĤ¯ãĥĪ
    -0.08
    pragma
    -0.08
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.09
    çĤĢ
    0.09
    æĥłåıĬ
    0.09
    uate
    0.09
    uy
    0.09
    owie
    0.09
    ahi
    0.09
    çīĴ
    0.09
    éĻŁ
    0.08
    azo
    0.08
    Activations Density 0.007%

    No Known Activations