© 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. 61414
    Prev
    Next
    INDEX
    Explanations

    saw something that

    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
    erah
    -0.10
    ictions
    -0.10
    éĩįä¸Ń
    -0.10
    æĪijçŁ¥éģĵ
    -0.09
    å²ĺ
    -0.09
    edList
    -0.09
    essa
    -0.09
    éĺĸ
    -0.09
     gent
    -0.09
    ScreenWidth
    -0.09
    POSITIVE LOGITS
    èĩªå·±
    0.09
    å½ĸ
    0.09
    å¼ģ
    0.09
    è¿ľæĻ¯
    0.08
    ãĥŀãĥ¼
    0.08
     Bieber
    0.08
     BELOW
    0.08
    è¿ľå¤Ħ
    0.08
    chas
    0.08
    cars
    0.08
    Activations Density 0.196%

    No Known Activations