© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    in any way

    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
    held
    -0.09
    åij±
    -0.09
    ç°§
    -0.09
    ién
    -0.09
    æ°¸è¿ľä¸įä¼ļ
    -0.09
    æ´¾
    -0.08
    åĬłæĮģ
    -0.08
    gfx
    -0.08
    é«ĺæ¸ħ
    -0.08
    endency
    -0.08
    POSITIVE LOGITS
    ãĥĸãĥŃãĤ°
    0.10
    ç¼
    0.09
    åģļ个
    0.09
    ç»Ŀ大å¤ļæķ°
    0.08
    æĪijåľ¨
    0.08
    å°Ķæĸ¯
    0.08
    æĿľåħ°
    0.08
    dar
    0.08
    æħ°éĹ®
    0.08
    åħ®
    0.08
    Activations Density 0.047%

    No Known Activations