© 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. 3432
    Prev
    Next
    INDEX
    Explanations

    round of

    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
    ä¸Ģæĸ¹
    -0.10
    ä¸Ģ段
    -0.09
    æĭĦ
    -0.09
    dio
    -0.09
    StringBuilder
    -0.09
    ç»°
    -0.09
    æĹłæīĢè°ĵ
    -0.09
    ä¸Ģ声
    -0.08
    aldi
    -0.08
     recurse
    -0.08
    POSITIVE LOGITS
     efforts
    0.09
    _tem
    0.09
    泯
    0.08
    ernal
    0.08
    Specifier
    0.08
    è¿ijè·Ŀ离
    0.08
    å¥ij
    0.08
    æĶ¹éĿ©
    0.08
    -night
    0.08
    otive
    0.08
    Activations Density 0.041%

    No Known Activations