© 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. 2564
    Prev
    Next
    INDEX
    Explanations

    manipulated into activity

    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
    æ¸ĹéĢı
    -0.09
    STANCE
    -0.09
    åħ¸ç¤¼
    -0.09
    æijĦ
    -0.08
    èĽŁ
    -0.08
    é¢ĦçķĻ
    -0.08
     ÑģкоÑĢо
    -0.08
    lie
    -0.08
     Daw
    -0.08
    รา
    -0.08
    POSITIVE LOGITS
     into
    0.14
    _into
    0.12
    Into
    0.11
     INTO
    0.11
    into
    0.11
     Into
    0.11
     ÑĥдалоÑģÑĮ
    0.10
    以为
    0.10
    èIJ½åħ¥
    0.10
    æĢĤ
    0.09
    Activations Density 0.172%

    No Known Activations