© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    legal actions and filings

    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
    å½ĵåľ°çļĦ
    -0.10
    æįķ
    -0.09
    å±ıå¹ķä¸Ĭ
    -0.09
    åı¯éĿłçļĦ
    -0.09
    èŀį
    -0.09
    ç©°
    -0.09
    /dialog
    -0.09
    _strerror
    -0.08
    éĤ£è¾¹
    -0.08
    å±ı
    -0.08
    POSITIVE LOGITS
    æݧ
    0.12
    两çĤ¹
    0.08
     corr
    0.08
    пÑĢоÑģ
    0.08
    æģIJ
    0.08
    ware
    0.08
    æ¶īæ¡Ī
    0.08
    åı¯ä¾Ľ
    0.08
    è¶ħ
    0.07
    责令
    0.07
    Activations Density 0.132%

    No Known Activations