© 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. 29829
    Prev
    Next
    INDEX
    Explanations

    Hartmut, Hartmann, Hart County

    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
    ìļĶ
    -0.11
    çªŁ
    -0.10
    æŃ¤é¡¹
    -0.09
    åĩłå®¶
    -0.09
    æ²»çIJĨä½ĵç³»
    -0.09
    å¨ĺ家
    -0.09
    åħ¶ä»ĸ人
    -0.09
     FRIEND
    -0.09
     ÙĪاÙĦØ£
    -0.09
    cean
    -0.08
    POSITIVE LOGITS
    ificial
    0.11
    fully
    0.11
    ifacts
    0.11
    iculo
    0.11
    uele
    0.10
    ness
    0.10
    ually
    0.10
     ness
    0.10
    mann
    0.09
    ening
    0.09
    Activations Density 0.018%

    No Known Activations