© 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. 5632
    Prev
    Next
    INDEX
    Explanations

    you hope to enjoy

    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
    宫
    -0.11
    å¥ijæľº
    -0.09
    å®®
    -0.09
    ç»ĻåĪ«äºº
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    éĩijå±±
    -0.08
    ç½ijè´Ń
    -0.08
    ç¥ī
    -0.08
    éĥ½ä¸įçŁ¥éģĵ
    -0.08
    èŃ¦ç¤º
    -0.08
    POSITIVE LOGITS
    çĪ°
    0.09
    åĬ¡
    0.09
    _beta
    0.09
    angelog
    0.08
    eldon
    0.08
    满æĦı
    0.08
    Flo
    0.08
     commun
    0.08
    çݳ
    0.08
    onda
    0.08
    Activations Density 0.024%

    No Known Activations