© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22207
    Prev
    Next
    INDEX
    Explanations

    ship terms

    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
    .cgi
    -0.09
    ä½ĵ温
    -0.09
    éĹ·
    -0.09
    æĴ©
    -0.09
    çĽ¼
    -0.08
     единÑģÑĤв
    -0.08
    segment
    -0.08
    çıł
    -0.08
    å±ħ家
    -0.08
     gent
    -0.08
    POSITIVE LOGITS
    æµħ
    0.11
    _Profile
    0.10
    ç¢į
    0.09
    æ¿ł
    0.09
    åľ°å½¢
    0.09
    å²©çŁ³
    0.09
     NEGLIGENCE
    0.09
    æ·º
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    DIC
    0.08
    Activations Density 0.059%

    No Known Activations