© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    fruit and ingredient mixture

    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
    å¢ī
    -0.09
     ÑıнваÑĢÑı
    -0.09
    _DISK
    -0.09
     **)&
    -0.09
    Ủ
    -0.09
    etus
    -0.08
    è·³
    -0.08
    ethe
    -0.08
     Zuk
    -0.08
    åĬ£
    -0.08
    POSITIVE LOGITS
    çĵ¦
    0.11
    èĽŁ
    0.10
    é½IJ
    0.10
    imb
    0.09
    éŀį
    0.09
    è£ģ
    0.09
     Mast
    0.09
    ç»Ń
    0.09
    æĿĤå¿Ĺ社
    0.09
    quete
    0.08
    Activations Density 0.072%

    No Known Activations