© 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. 62180
    Prev
    Next
    INDEX
    Explanations

    enter virtual world

    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
    ÑĦин
    -0.10
    kaar
    -0.09
    moment
    -0.08
    verture
    -0.08
    å®Įç¾İçļĦ
    -0.08
    æī¯
    -0.08
    ãĤıãĤĬ
    -0.08
    даÑĩи
    -0.08
    ÐľÐIJ
    -0.08
    xee
    -0.08
    POSITIVE LOGITS
    è¡ĮåĪĹ
    0.11
    prising
    0.10
    CriticalSection
    0.10
    æĭ¥
    0.09
     Ñģвое
    0.09
    è¿Ľåħ¥äºĨ
    0.09
    poss
    0.09
     poss
    0.09
    .enter
    0.09
    å£ģåŀĴ
    0.09
    Activations Density 0.077%

    No Known Activations