© 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. 22421
    Prev
    Next
    INDEX
    Explanations

    computer peripheral devices

    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
    éĹ©
    -0.10
    оÑĤов
    -0.09
    åĶ¯
    -0.08
    çķª
    -0.08
    /apps
    -0.08
     intercept
    -0.08
    çª
    -0.08
    è·ij
    -0.08
    æĦĪ
    -0.08
    饼
    -0.08
    POSITIVE LOGITS
    éĶ®çĽĺ
    0.12
    å¤ĸåĽ´
    0.11
    è¾ĵåħ¥
    0.11
    é¼łæłĩ
    0.11
    å¯Į
    0.09
    çŁ³å¤´
    0.09
     input
    0.09
     keyboard
    0.09
    .pen
    0.09
    	mouse
    0.09
    Activations Density 0.079%

    No Known Activations