© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    ch words

    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
    soever
    -0.09
    æ²±
    -0.09
     Erect
    -0.08
    ัà¸ģษ
    -0.08
    oretical
    -0.08
    æĸ½
    -0.08
    наÑĩ
    -0.08
    ä¸įæĺİ
    -0.08
    portun
    -0.08
    odka
    -0.08
    POSITIVE LOGITS
    æķŀå¼Ģ
    0.09
    /dr
    0.09
    æµij身
    0.09
    _rp
    0.09
    halb
    0.09
    -ch
    0.09
    æŁŀ
    0.09
    轶
    0.09
    æłijåı¶
    0.08
    éĴ³
    0.08
    Activations Density 0.014%

    No Known Activations