© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51458
    Prev
    Next
    INDEX
    Explanations

    cannot believe

    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
    è¡Ķ
    -0.09
    æĥĨ
    -0.09
    ле
    -0.09
    æľ¬è´¨ä¸Ĭ
    -0.09
    æħ°
    -0.08
    liced
    -0.08
    é£İæݧ
    -0.08
     SCORE
    -0.08
    bie
    -0.08
    é¢Ħæ¡Ī
    -0.08
    POSITIVE LOGITS
    秽
    0.10
    ingly
    0.09
    ably
    0.09
     диагноÑģÑĤ
    0.09
    ÙģاÙĤ
    0.09
    ley
    0.09
    nor
    0.08
    _finished
    0.08
    æĴħ
    0.08
    åıĮæīĭ
    0.08
    Activations Density 0.003%

    No Known Activations