© 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. 1110
    Prev
    Next
    INDEX
    Explanations

    must retain

    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
    滥
    -0.10
    åĢ¡
    -0.10
    æĹłæķ°
    -0.10
    为é¦ĸ
    -0.10
    hoot
    -0.09
    ç¿ķ
    -0.09
    .opend
    -0.09
    廪
    -0.09
    åıªä¸º
    -0.09
    éĿ¡
    -0.09
    POSITIVE LOGITS
    åľ°å¸¦
    0.09
    积æŀģä½ľçĶ¨
    0.09
    èįī
    0.08
    èģĮ
    0.08
    åijĪ
    0.08
    rop
    0.07
     ohio
    0.07
     STATS
    0.07
     Pall
    0.07
    å½±åĵįåĬĽçļĦ
    0.07
    Activations Density 0.005%

    No Known Activations