© 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. 63514
    Prev
    Next
    INDEX
    Explanations

    ask, present, challenge, invite, suggest, announce

    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
    usher
    -0.10
    帮åĬ©
    -0.09
    ä»ĸæĽ¾
    -0.09
    åıł
    -0.08
    æ²£
    -0.08
     PRES
    -0.08
    leigh
    -0.08
    гÑĢан
    -0.08
    侥幸
    -0.08
    好å¤ļ
    -0.08
    POSITIVE LOGITS
     hereby
    0.13
    è°¨
    0.12
    å¥ī
    0.10
    æŶä¸į
    0.09
    éĥijéĩį
    0.09
    :invoke
    0.08
     вам
    0.08
    çĻ¾èĬ±
    0.08
    æѤ
    0.08
     herein
    0.08
    Activations Density 0.130%

    No Known Activations