© 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. 61894
    Prev
    Next
    INDEX
    Explanations

    is governed by license

    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
    å³Ļ
    -0.10
    éĻ©
    -0.09
    åºĸ
    -0.09
     facilit
    -0.09
    æ´ĭèij±
    -0.09
    åĪĨè£Ĥ
    -0.09
    è¿ľæĸ¹
    -0.09
    æĮº
    -0.09
    æĭ¯æķij
    -0.08
    éļ¨
    -0.08
    POSITIVE LOGITS
    _TUN
    0.09
    åįĥ亿
    0.08
    Boot
    0.08
    èĮ¹
    0.08
    /boot
    0.08
    çŀĴ
    0.08
    ä¸įè¡Į
    0.08
    áp
    0.07
    _boot
    0.07
     Boot
    0.07
    Activations Density 0.370%

    No Known Activations