© 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. 47852
    Prev
    Next
    INDEX
    Explanations

    names like Thompson, Zoe, Founder, Finger

    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
    adel
    -0.09
    Congratulations
    -0.09
    èĴ¸
    -0.08
    å¹²
    -0.08
    æłĩé¢ĺ
    -0.07
    animation
    -0.07
    åĭĩæ°Ķ
    -0.07
    ç¹ģ
    -0.07
    çij¶
    -0.07
    æݨ
    -0.07
    POSITIVE LOGITS
    亲èĩª
    0.13
    æķĻä½ł
    0.12
    å°±ç»Ļ大家
    0.11
    ä½ķåĨµ
    0.10
    ä»ĸä¼ļ
    0.09
     лиÑĩно
    0.09
    åħ¨åĬĽæīĵéĢł
    0.09
    çĩļ
    0.09
    å·¥ç¨ĭå¸Ī
    0.09
    ä¸įä»ħèĥ½
    0.09
    Activations Density 0.065%

    No Known Activations