© 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. 62951
    Prev
    Next
    INDEX
    Explanations

    have we here

    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
    letic
    -0.10
    è¾ŀ
    -0.10
    éĥ½ä¼ļæľī
    -0.09
    orage
    -0.09
    åıĤ
    -0.09
    å¦Ĥæŀľæ²¡æľī
    -0.09
    èľķ
    -0.09
    沧å·ŀ
    -0.09
     RH
    -0.08
    èģĶç³»çĶµè¯Ŀ
    -0.08
    POSITIVE LOGITS
    å¾ĴæŃ¥
    0.09
    eya
    0.08
    eka
    0.08
    iez
    0.08
    éģ¥æݧ
    0.08
    agne
    0.08
     Streets
    0.08
    å··
    0.08
    ä¸Ģ份
    0.08
    agn
    0.08
    Activations Density 0.013%

    No Known Activations