© 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. 58761
    Prev
    Next
    INDEX
    Explanations

    dean of

    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
    å®ĹæŨ
    -0.09
    ç»Ń
    -0.09
    arker
    -0.09
     bó
    -0.09
    åİļåİļ
    -0.09
    强çĥĪçļĦ
    -0.08
    å±Ģå±Ģéķ¿
    -0.08
    ãĤ¿ãĤ¤ãĥĪãĥ«
    -0.08
     Lighting
    -0.08
    æ°¨åŁº
    -0.08
    POSITIVE LOGITS
    å°ıäºĭ
    0.09
    acy
    0.09
    alty
    0.09
     precip
    0.09
    acies
    0.09
    天ä¸ĭ
    0.09
     polar
    0.08
    å¨ĺå¨ĺ
    0.08
    [code
    0.08
     Marsh
    0.08
    Activations Density 0.009%

    No Known Activations