© 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. 31757
    Prev
    Next
    INDEX
    Explanations

    composition, form, representation

    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
    æ¾į
    -0.09
    lest
    -0.08
    è¡
    -0.08
    .portal
    -0.08
     Ñģамо
    -0.08
    orage
    -0.08
    fur
    -0.08
    è¾ķ
    -0.08
    ysz
    -0.08
    è´¡
    -0.08
    POSITIVE LOGITS
    çī©ä½ĵ
    0.11
    å¸ĥå±Ģ
    0.10
    æĤ¬
    0.10
    æĦŁ
    0.09
    .Serve
    0.09
    liquid
    0.09
    å±Ĥ次
    0.09
    ä½ĵéĩı
    0.09
     Bundy
    0.08
    odu
    0.08
    Activations Density 0.062%

    No Known Activations