© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    to follow

    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
     Lun
    -0.09
    adin
    -0.09
    acades
    -0.09
    ivity
    -0.09
     конÑĤÑĢ
    -0.09
    عش
    -0.09
    /editor
    -0.08
    coder
    -0.08
    å°Ħ
    -0.08
    .sap
    -0.08
    POSITIVE LOGITS
    æĦŁåıĹåĪ°äºĨ
    0.11
    çı
    0.10
    èģļä¼ļ
    0.09
    å¦Ĥä½ķåİ»
    0.09
    å¤ĸåįĸ
    0.09
    å«ĸ
    0.08
    oken
    0.08
    éĥ½åĸľæ¬¢
    0.08
    å¿¿
    0.08
    èĩ³äºİ
    0.08
    Activations Density 0.018%

    No Known Activations