© 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. 34513
    Prev
    Next
    INDEX
    Explanations

    were, like, going, into

    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
    ç»ĵ
    -0.09
    沤
    -0.09
    泡沫
    -0.08
     foam
    -0.08
    åħ³éĶ®æĬĢæľ¯
    -0.08
    æīĭä¸ĭ
    -0.08
    浯
    -0.08
     fo
    -0.08
     Foam
    -0.08
    èľ·
    -0.08
    POSITIVE LOGITS
    åĽŀåĪ°äºĨ
    0.10
    仿
    0.09
    è¿Ľåħ¥äºĨ
    0.09
    æīĵåħ¥
    0.09
    置身
    0.09
    ullet
    0.09
    arters
    0.09
    æīįæĺ¯çľŁæŃ£
    0.09
    .land
    0.08
    åİĨå¹´
    0.08
    Activations Density 0.034%

    No Known Activations