© 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. 33629
    Prev
    Next
    INDEX
    Explanations

    pricing and changes

    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
    çIJĨæĥ³ä¿¡å¿µ
    -0.10
    çŃĶå¤į
    -0.09
    æ±
    -0.09
    çĶ©
    -0.08
    纪å¾ĭ
    -0.08
    å¿ĹæĦ¿
    -0.08
    ä¸ĩéĩĮ
    -0.08
    ç¾İ好
    -0.08
    PCS
    -0.08
    åŁºéĩijç»ıçIJĨ
    -0.08
    POSITIVE LOGITS
    æµ®åĬ¨
    0.10
    纡
    0.09
    åľ°åĮº
    0.09
     اÙĦÙħع
    0.08
    åħ¸
    0.08
    åĥĸ
    0.08
    çķ¸
    0.08
     FINAL
    0.08
    íķŃ
    0.08
    onium
    0.08
    Activations Density 0.021%

    No Known Activations