© 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. 55153
    Prev
    Next
    INDEX
    Explanations

    till fully dissolved

    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
    innie
    -0.09
    éļıå¤Ħ
    -0.09
    æĪĺæĸĹ
    -0.09
    沸èħ¾
    -0.09
    è¾£
    -0.09
    ä½ı
    -0.09
    å¿ħä¸įåı¯
    -0.09
    å¨ģåĬĽ
    -0.09
    LLU
    -0.09
    åģı好
    -0.09
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.10
     together
    0.10
    åĩºéģĵ
    0.09
    SENT
    0.08
    ç¿ķ
    0.08
    æ±ĩæĢ»
    0.08
     fan
    0.08
    enta
    0.08
    çĭŃ
    0.08
    ока
    0.08
    Activations Density 0.008%

    No Known Activations