© 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. 58676
    Prev
    Next
    INDEX
    Explanations

    told [entity]

    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
    ä¸IJ
    -0.09
    éŀ
    -0.09
    æ´Ĺ
    -0.09
    羣çļĦ
    -0.08
    çħ¦
    -0.08
    楸
    -0.08
     Cush
    -0.08
    绣
    -0.08
    uge
    -0.08
    åħ±åIJĮåıijå±ķ
    -0.08
    POSITIVE LOGITS
    åijĬè¯ī
    0.11
    æµĭç®Ĺ
    0.09
     tale
    0.09
    åijĬè¯ī她
    0.09
    æ²Ī
    0.09
    å¥ij约
    0.09
    èĥĨ
    0.09
    IGNED
    0.08
     пÑĢимеÑĢ
    0.08
     %+
    0.08
    Activations Density 0.015%

    No Known Activations