© 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. 31058
    Prev
    Next
    INDEX
    Explanations

    signing books and events

    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
    大æ°Ķ
    -0.10
    åħ·æľīä¸Ģå®ļ
    -0.09
    éĿ¢è²Į
    -0.09
    اÙħت
    -0.09
    _ep
    -0.09
    æ³ķå¾ĭ顾éĹ®
    -0.08
    Ep
    -0.08
    å§ij
    -0.08
     expend
    -0.08
    oron
    -0.08
    POSITIVE LOGITS
    itti
    0.10
    缯
    0.09
    çĸĻ
    0.09
    aling
    0.09
    è£Ĩ
    0.08
    à¹Ģà¸Ħ
    0.08
    ç»
    0.08
    dam
    0.08
    ored
    0.08
    å»ī
    0.08
    Activations Density 0.006%

    No Known Activations