© 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. 3311
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    åĩ«
    -0.12
     полÑĥÑĩен
    -0.10
    å®īåħ¨æĦŁ
    -0.09
    å¾ĹäºĨ
    -0.09
    è¿Ļ件äºĭ
    -0.09
     öd
    -0.09
     UNUSED
    -0.09
    äºĨä¸ĢäºĽ
    -0.09
    felt
    -0.09
    æĪIJåĬŁçİĩ
    -0.09
    POSITIVE LOGITS
    æĭ¿åĩºæĿ¥
    0.10
    åħ¥æīĭ
    0.09
    asts
    0.09
    亲èĩª
    0.09
    .histogram
    0.08
     воÑĤ
    0.08
    ockey
    0.08
    à¸Ļำมา
    0.08
     vac
    0.08
    çĶ¨æĿ¥
    0.08
    Activations Density 0.047%

    No Known Activations