© 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. 17591
    Prev
    Next
    INDEX
    Explanations

    available

    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
    辫
    -0.10
    çķĻä½ı
    -0.10
    åĸ½
    -0.09
    _cre
    -0.09
     cooperate
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    èĿ¶
    -0.09
    趾
    -0.09
     Rug
    -0.08
    ugu
    -0.08
    POSITIVE LOGITS
    NEXT
    0.09
    /generated
    0.09
    å¯¹æľªæĿ¥
    0.08
    çľĭæĿ¥
    0.08
    å»Ľ
    0.08
    两级
    0.08
    elo
    0.08
    åħ·æľī
    0.08
    JOR
    0.08
    æºIJ
    0.08
    Activations Density 0.320%

    No Known Activations