© 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. 34595
    Prev
    Next
    INDEX
    Explanations

    reported speech attribution

    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
    æĺ¯éŁ©åĽ½
    -0.10
    äºĨäºĽ
    -0.10
    计ç®ĹåĻ¨
    -0.10
    åĶī
    -0.09
    CppType
    -0.09
    ä½ĨæĪij们
    -0.09
    onor
    -0.09
    éľĨ
    -0.09
    åĽłä¸ºæĪij们
    -0.09
    éĶĻäºĨ
    -0.09
    POSITIVE LOGITS
    ä»ĸ对
    0.09
    ä»ĸ
    0.09
    她
    0.08
    ä»ĸå°±
    0.08
     him
    0.08
    åīįèĢħ
    0.08
    nya
    0.08
    uble
    0.07
    ä»ĸä¹Ł
    0.07
    æľ¬èº«å°±
    0.07
    Activations Density 0.015%

    No Known Activations