© 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. 56478
    Prev
    Next
    INDEX
    Explanations

    common phrases and descriptions

    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
    çݯå¢ĥ污æŁĵ
    -0.10
    çݯå¢ĥä¿ĿæĬ¤
    -0.09
    .lv
    -0.09
    é¡¹çĽ®å»ºè®¾
    -0.09
    çīĩåĪ»
    -0.08
    读åIJİ
    -0.08
    raises
    -0.08
     Chic
    -0.08
    çĶ³
    -0.08
    åİļåİļ
    -0.08
    POSITIVE LOGITS
    çħľ
    0.09
    iano
    0.09
    å¾ģä¿¡
    0.08
    å®ĮåĸĦ
    0.08
     Hal
    0.08
    еÑĢиал
    0.08
    å»ī
    0.08
    ç¹ģ
    0.08
    åģļäºĭ
    0.08
    管çIJĨç³»ç»Ł
    0.08
    Activations Density 0.048%

    No Known Activations