© 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. 58052
    Prev
    Next
    INDEX
    Explanations

    salami, pickles, sandía, shoestring

    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
    ì§ij
    -0.10
    æĭĬ
    -0.09
    rien
    -0.09
    Unt
    -0.09
     Dil
    -0.09
    زÙĨ
    -0.09
     Richmond
    -0.09
    naments
    -0.09
    _Double
    -0.08
    éĥ½è¯´
    -0.08
    POSITIVE LOGITS
    äºĨ解åĪ°
    0.09
    own
    0.08
    éľĦ
    0.08
    è¿ĻèĪ¬
    0.08
    çĶ°
    0.08
    iss
    0.08
    ä¹Łä¸įæĥ³
    0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.07
    æī«é»ij
    0.07
    å¥īçĮ®
    0.07
    Activations Density 0.109%

    No Known Activations