© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52851
    Prev
    Next
    INDEX
    Explanations

    cr words

    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
     Fur
    -0.09
    çħ¦
    -0.09
    oft
    -0.09
    etta
    -0.09
    å®ļå¾ĭ
    -0.08
     fur
    -0.08
    ä»ĵåºĵ
    -0.08
    ichi
    -0.08
     retract
    -0.08
     cá»Ń
    -0.08
    POSITIVE LOGITS
     Cr
    0.10
    (cr
    0.10
     cr
    0.10
    æį·
    0.10
     crud
    0.09
    å°±åľ¨äºİ
    0.09
    óst
    0.09
    .formData
    0.09
     Mario
    0.08
    èĢį
    0.08
    Activations Density 0.037%

    No Known Activations