© 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. 61307
    Prev
    Next
    INDEX
    Explanations

    will suffice

    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
    祺
    -0.10
    izo
    -0.10
    éľĩ
    -0.10
    ableView
    -0.09
    主æĿĥ
    -0.08
    <![
    -0.08
    çĽĤ
    -0.08
    rewrite
    -0.08
    FLT
    -0.08
    æĢİä¹Īä¼ļ
    -0.08
    POSITIVE LOGITS
    å°±å¤ŁäºĨ
    0.18
    å°±åı¯ä»¥äºĨ
    0.16
    å°±è¡ĮäºĨ
    0.15
    å°±å¤Ł
    0.14
    å°±è¡Į
    0.14
     suffice
    0.13
    åį³åı¯
    0.12
    就好äºĨ
    0.12
    åıªéľĢ
    0.12
    ç®ĹäºĨ
    0.12
    Activations Density 0.038%

    No Known Activations