© 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. 6667
    Prev
    Next
    INDEX
    Explanations

    list of companies

    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
    ä¹IJåĽŃ
    -0.10
    zano
    -0.09
    ä¸ĵå¿ĥ
    -0.09
    ç§ĺ书éķ¿
    -0.09
    cul
    -0.09
    çĩ®
    -0.09
    屯
    -0.09
    ä¿Ŀå§Ĩ
    -0.09
    éĻįåĪ°
    -0.08
    骥
    -0.08
    POSITIVE LOGITS
    çĺ¤
    0.08
    身ä½ĵ
    0.07
    etri
    0.07
    å°±èĥ½å¤Ł
    0.07
    åŃķ
    0.07
    .png
    0.07
    Lewis
    0.07
    ãĤĤãģ®
    0.07
    å³°
    0.07
    TS
    0.07
    Activations Density 0.085%

    No Known Activations