© 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. 35184
    Prev
    Next
    INDEX
    Explanations

    work out

    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
    佶
    -0.10
    å·¥ä½ľæĢ»ç»ĵ
    -0.10
    æĪĺå½¹
    -0.09
    俯
    -0.09
    esson
    -0.09
    @email
    -0.09
     اÙĦآخر
    -0.09
    fir
    -0.09
     küç
    -0.09
    idis
    -0.09
    POSITIVE LOGITS
     Cra
    0.10
    人å±ħ
    0.09
    rais
    0.09
    åĨįä¹Łä¸į
    0.09
    ÑĢÑĭв
    0.08
    è°ĥ
    0.08
    èĤ±
    0.08
    ä¹IJæĦı
    0.07
    lover
    0.07
    èĩªåľ¨
    0.07
    Activations Density 0.007%

    No Known Activations