© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    æĺ¥å¤ı
    -0.10
    好çļĦ
    -0.09
    å¥ĩ
    -0.08
    onium
    -0.08
    /fast
    -0.08
    çļĦåĪ°æĿ¥
    -0.08
    bild
    -0.08
    TOR
    -0.08
    ãģ¾ãĤĬ
    -0.07
     sourceMapping
    -0.07
    POSITIVE LOGITS
    å®Įç»ĵ
    0.09
    alis
    0.09
    ãĤį
    0.09
    ely
    0.09
    们çļĦ
    0.09
    ously
    0.09
    ãĤ
    0.09
    å±¥èģĮ
    0.09
    è¿ĻæĿ¡è·¯
    0.08
    ally
    0.08
    Activations Density 0.021%

    No Known Activations