© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
    åģĥ
    -0.10
    ĺ认
    -0.10
    yna
    -0.10
    .isFile
    -0.09
    çĭ¼
    -0.09
    èĦĶ
    -0.08
    汤
    -0.08
    离
    -0.08
    INES
    -0.08
    ulares
    -0.08
    POSITIVE LOGITS
    åij¨è½¬
    0.13
    秣
    0.09
    èĩªæľī
    0.09
    ç§Łè½¦
    0.09
    ä¸ĵ人
    0.09
    achel
    0.09
    åªĴ
    0.09
    æī«ä¸Ģæī«
    0.09
    è¿Ķè¿ĺ
    0.09
     rot
    0.08
    Activations Density 0.075%

    No Known Activations