© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21628
    Prev
    Next
    INDEX
    Explanations

    circular range, buf, fluorescent, boxes, cross, race, promise, dich

    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
    ðŁı»
    -0.09
    æĮļ
    -0.09
    æĭ¢
    -0.09
    çĿ£
    -0.09
    UTOR
    -0.09
    人çļĦ
    -0.09
    ervative
    -0.09
    ðŁı¼
    -0.09
    ราว
    -0.09
    èĸĦå¼±
    -0.08
    POSITIVE LOGITS
    ly
    0.15
    ities
    0.14
    à¹Į
    0.10
    ict
    0.10
    ity
    0.10
    mente
    0.09
    omon
    0.09
     minded
    0.09
    ï¸ı
    0.08
    idad
    0.08
    Activations Density 0.045%

    No Known Activations