© 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. 50129
    Prev
    Next
    INDEX
    Explanations

    verbs expressing intent or belief

    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
    åľ¨æİ¥åıĹ
    -0.10
    åĪ°è¿ĻéĩĮ
    -0.09
    åľ¨è¿Ļç§į
    -0.09
    ç©¿éĢı
    -0.09
    STAR
    -0.09
    对æѤ
    -0.09
    _pes
    -0.09
    äººæł¼
    -0.09
    lez
    -0.09
    chet
    -0.08
    POSITIVE LOGITS
    ikes
    0.09
    Bright
    0.09
    ık
    0.08
    æĥļ
    0.08
     (>
    0.08
    å¥ī
    0.08
    ::
    0.08
    andel
    0.08
    eny
    0.07
    в
    0.07
    Activations Density 0.122%

    No Known Activations