© 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. 61748
    Prev
    Next
    INDEX
    Explanations

    special characters and non-english words

    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
    çĦ¦
    -0.10
    è¿Ļæīį
    -0.10
    éĻ¤å¤ĸ
    -0.10
    ude
    -0.10
    æŃ¤ä¸¾
    -0.09
    æıł
    -0.09
    è§Ħç«ł
    -0.09
     Stella
    -0.09
    ä¸ĭéĿ¢å°±
    -0.09
    亮çĤ¹
    -0.09
    POSITIVE LOGITS
    eya
    0.08
    oir
    0.08
    åħį
    0.08
    hog
    0.08
    æĹ¢è¦ģ
    0.08
    åĿĽ
    0.07
    â½´
    0.07
    ensa
    0.07
    æ¦Ĩ
    0.07
    æ¡©
    0.07
    Activations Density 0.241%

    No Known Activations