© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38422
    Prev
    Next
    INDEX
    Explanations

    it, these, them

    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
    orent
    -0.10
    ersion
    -0.08
    ÑģÑĮ
    -0.08
    pins
    -0.08
    emos
    -0.08
    èĩªå·±
    -0.08
    ras
    -0.08
     narc
    -0.08
    ä¹Łå¥½
    -0.08
    ega
    -0.07
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.09
    å²IJ
    0.09
    æĴµ
    0.09
    妥
    0.09
     setType
    0.09
    黯
    0.08
    èĩ´æķ¬
    0.08
    äº®çĽ¸
    0.08
    recipe
    0.08
    å¾Ħ
    0.08
    Activations Density 0.181%

    No Known Activations