© 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. 51070
    Prev
    Next
    INDEX
    Explanations

    quarry and construction

    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
    è¿Ĥ
    -0.10
    çĶµå·¥
    -0.09
    èĬĤæĹ¥
    -0.09
    æ¾
    -0.09
    GIT
    -0.09
    è¿IJ转
    -0.09
    çķ¦
    -0.09
     помеÑīениÑı
    -0.09
    马æĭīæĿ¾
    -0.09
    è´¢ç¨İ
    -0.09
    POSITIVE LOGITS
    è´±
    0.10
     quarry
    0.10
    æŀķ
    0.09
     gravel
    0.09
    _CNTL
    0.09
    è½®å»ĵ
    0.08
    èµĦè´¨
    0.08
    çłĤ
    0.08
    碾
    0.08
    çŃĽ
    0.08
    Activations Density 0.062%

    No Known Activations