© 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. 34350
    Prev
    Next
    INDEX
    Explanations

    requires javascript

    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
    æĪij以为
    -0.09
    æĢı
    -0.09
    ingly
    -0.09
    edException
    -0.09
    ford
    -0.09
    äºĨæĪijçļĦ
    -0.08
    äºİ
    -0.08
    赶ä¸Ĭ
    -0.08
    Destructor
    -0.08
    ecessarily
    -0.08
    POSITIVE LOGITS
    iamond
    0.09
    AGES
    0.09
    éĻĭ
    0.09
    æ»ĭåij³
    0.08
    èĥ½å¾ĹåĪ°
    0.08
    ÑĤÑı
    0.08
    类似
    0.08
    è´¢å¯Į
    0.08
    åIJİæľŁ
    0.08
    å°±è¿Ļä¹Ī
    0.08
    Activations Density 0.002%

    No Known Activations