© 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. 39006
    Prev
    Next
    INDEX
    Explanations

    first

    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
    лаг
    -0.09
    éĺ´
    -0.08
    iniz
    -0.08
    å½ĵåīį
    -0.08
    elijk
    -0.08
    就好
    -0.08
    è¿ĺæĺ¯è¦ģ
    -0.08
    VEL
    -0.08
    çľĭ书
    -0.08
    \Container
    -0.08
    POSITIVE LOGITS
    -ever
    0.14
     ever
    0.14
    ä»İæĿ¥æ²¡
    0.13
     EVER
    0.12
    羣æŃ£çļĦ
    0.12
    大è§Ħ模
    0.11
    å®Įæķ´çļĦ
    0.11
    è¿Ļä¹Īä¹ħ
    0.11
    羣æŃ£
    0.11
    ä»İæĿ¥æ²¡æľī
    0.11
    Activations Density 0.237%

    No Known Activations