© 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. 10258
    Prev
    Next
    INDEX
    Explanations

    speaker components or questions

    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
    龸
    -0.10
    æ±½
    -0.09
    ç£Ķ
    -0.09
    å¹Į
    -0.09
    æĿ³
    -0.09
    elen
    -0.09
     RAND
    -0.09
     pav
    -0.09
     Jet
    -0.09
     Trans
    -0.09
    POSITIVE LOGITS
    죽
    0.09
    çľĭå¾Ĺ
    0.09
     kit
    0.09
    LEM
    0.08
    å¤ļ彩
    0.08
    ErrorMsg
    0.08
     Pe
    0.08
    èĿī
    0.08
    ungan
    0.08
    代è¨Ģ
    0.08
    Activations Density 0.096%

    No Known Activations