© 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. 30190
    Prev
    Next
    INDEX
    Explanations

    season ranges

    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
    dÃŃ
    -0.09
    äºĨä¸Ģ份
    -0.09
    çݲ
    -0.09
    UpdatedAt
    -0.08
    樵
    -0.08
    篱
    -0.08
    æĹ©åľ¨
    -0.08
    isoft
    -0.08
    jal
    -0.08
    夫
    -0.08
    POSITIVE LOGITS
    æıIJåĩºçļĦ
    0.10
    以ä¾Ĩ
    0.09
    æľŁéĹ´
    0.09
     baÅŁÄ±nda
    0.09
     onwards
    0.09
    æĻĤçĤ¹ãģ§
    0.09
    ç¨įç¨į
    0.09
    å¹´éĹ´
    0.08
    åı¯èĥ½åıijçĶŁ
    0.08
    å±Ĭ
    0.08
    Activations Density 0.067%

    No Known Activations