© 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. 3434
    Prev
    Next
    INDEX
    Explanations

    this essay, action, episode, contest, two, series, story, study

    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
    çļĦåľ°ä½į
    -0.09
    éĺ¼
    -0.09
    çłģ
    -0.08
    åĻ«
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
    èĺħ
    -0.08
    ارات
    -0.08
     amount
    -0.08
    æħķ
    -0.08
    åIJİå¤ĩ
    -0.08
    POSITIVE LOGITS
    åŁİ乡
    0.10
    geo
    0.09
    å®Įç¾İçļĦ
    0.09
    åĿļ
    0.09
    ioc
    0.09
    严峻
    0.09
    庶
    0.09
    éĥ¢
    0.08
     коÑĤоÑĢого
    0.08
    ape
    0.08
    Activations Density 0.226%

    No Known Activations