© 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. 57611
    Prev
    Next
    INDEX
    Explanations

    by

    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
    绢
    -0.09
    æĭį
    -0.09
    æľīéĹ®é¢ĺ
    -0.09
    å°ī
    -0.09
    ially
    -0.08
    踩
    -0.08
    究
    -0.08
    以人为
    -0.08
    urch
    -0.08
     Rout
    -0.08
    POSITIVE LOGITS
     standards
    0.17
    çļĦçľ¼åħī
    0.12
    è§Ĵ度æĿ¥çľĭ
    0.12
    æĿ¥è¯´
    0.11
     Standards
    0.11
    çľ¼çľĭ
    0.10
    è§Ĩè§Ĵ
    0.10
    åħ¬è®¤çļĦ
    0.10
    çļĦè§Ĵ度
    0.10
    æĿ¥çľĭ
    0.10
    Activations Density 0.051%

    No Known Activations