© 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. 59051
    Prev
    Next
    INDEX
    Explanations

    photographic scene

    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
    лоÑĤ
    -0.09
    é«ĺå³°æľŁ
    -0.09
    èĬĻ
    -0.09
    çļĦ大
    -0.09
    ä½Ķ
    -0.08
    _SOUND
    -0.08
    çĶŁæ´»ä¸Ń
    -0.08
    ä¸Ģåı·
    -0.08
    大楼
    -0.08
    çĥŃæ°´
    -0.08
    POSITIVE LOGITS
    çĭ±
    0.10
    beit
    0.09
    裨
    0.09
     Ces
    0.08
    å¥ij
    0.08
    LIK
    0.08
    è¯Ħè®®
    0.08
    terms
    0.08
    èĿł
    0.08
    éĢ¸
    0.08
    Activations Density 0.091%

    No Known Activations