© 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. 31685
    Prev
    Next
    INDEX
    Explanations

    pathogens after path

    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
    ç¯Ŀ
    -0.09
    æĥľ
    -0.09
     пÑĢоведен
    -0.08
    æĥ¨
    -0.08
     Diss
    -0.08
    å¡Į
    -0.08
     intern
    -0.08
     Congressional
    -0.08
     embr
    -0.08
    ailable
    -0.07
    POSITIVE LOGITS
    èıĮ
    0.12
    ä¸Ģ群
    0.10
     bacteria
    0.10
    å¯Ħ
    0.09
    lops
    0.09
    ê·ł
    0.09
    代çIJĨ
    0.09
    AtPath
    0.09
    ä¸ĢåłĨ
    0.09
    ä¸Ģ大åłĨ
    0.09
    Activations Density 0.422%

    No Known Activations