© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19690
    Prev
    Next
    INDEX
    Explanations

    Cap, rio

    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
    æľ¬ç½ijç«Ļ
    -0.10
    çĽ¾
    -0.10
    stry
    -0.09
    èĥ¸åīį
    -0.09
    çī¢
    -0.09
    æĹ¥å¤ľ
    -0.09
    åŁİå¸Ĥ管çIJĨ
    -0.09
     lith
    -0.09
    éĺ²æĬ¤
    -0.08
    çĦĻ
    -0.08
    POSITIVE LOGITS
    èıħ
    0.09
    åħīèį£
    0.08
    æ³ķåĪ¶
    0.08
    è§Ħ磩
    0.08
     insol
    0.08
    dish
    0.08
     conven
    0.07
    è§Ħ
    0.07
    pron
    0.07
    oran
    0.07
    Activations Density 0.001%

    No Known Activations