© 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. 27316
    Prev
    Next
    INDEX
    Explanations

    developer`Core` / `ap` / `data` / `we` followed by specific tokens

    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
    éĺµ
    -0.09
    æŁĶ软
    -0.09
    æºĺ
    -0.09
    çĤ³
    -0.08
     каз
    -0.08
    éĩľ
    -0.08
    ãģŁãĤī
    -0.08
    æīĵæĬĺ
    -0.08
    otechn
    -0.08
    罪
    -0.08
    POSITIVE LOGITS
    æIJĶ
    0.11
    è¡®
    0.11
    chemy
    0.09
    æ§İ
    0.08
    åIJIJ槽
    0.08
    кÑĥп
    0.08
    ITOR
    0.08
    preload
    0.08
    sembly
    0.08
    osten
    0.08
    Activations Density 0.011%

    No Known Activations