© 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. 16975
    Prev
    Next
    INDEX
    Explanations

    bittersweet, love-hate, mixed feelings

    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
    å´½
    -0.09
    åĸĿ
    -0.09
    æ®ĸ
    -0.09
     Sav
    -0.09
    æ¾Ī
    -0.09
     обÑĭ
    -0.09
    磶
    -0.08
    ÑĢаÑģ
    -0.08
    urbation
    -0.08
    缦
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵèĩªå·±
    0.09
    æ¾Ħæ¸ħ
    0.09
    eter
    0.09
    æĶ¶èİ·
    0.08
    elson
    0.08
    calar
    0.08
    å¼Ģåıij建设
    0.08
    è¿ĻæĶ¯
    0.08
    wis
    0.08
    iams
    0.08
    Activations Density 0.005%

    No Known Activations