© 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. 57140
    Prev
    Next
    INDEX
    Explanations

    thumb up or thumb drive

    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
    icing
    -0.11
    Ñĩем
    -0.09
    ccount
    -0.08
    以æѤ
    -0.08
    è¶Ł
    -0.08
     Mushroom
    -0.08
    大èĦij
    -0.08
    Won
    -0.08
    	TokenName
    -0.08
    ining
    -0.08
    POSITIVE LOGITS
    /thumb
    0.11
    ature
    0.10
    thumbs
    0.10
    éĥ½è¯´
    0.10
    æIJ¦
    0.09
    æİīäºĨ
    0.09
    æĪij们åºĶ该
    0.09
     thumbs
    0.08
    alore
    0.08
    nı
    0.08
    Activations Density 0.011%

    No Known Activations