© 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. 62956
    Prev
    Next
    INDEX
    Explanations

    meeting or discussion

    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
    æľįå½¹
    -0.10
    æ²¾
    -0.09
    ial
    -0.09
    好äºĨ
    -0.09
    ecz
    -0.08
    诸
    -0.08
    ä½ıäºĨ
    -0.08
    ilater
    -0.08
    oom
    -0.08
    è¿ĩåħ³
    -0.08
    POSITIVE LOGITS
    æĪijä¸įæĥ³
    0.11
    纲
    0.10
    èįIJ
    0.09
    æĻ¯å¾·
    0.09
    对æĪijæĿ¥è¯´
    0.09
    ÑĢоÑģÑĤ
    0.09
    åīįä»»
    0.09
     Armour
    0.09
    AdapterFactory
    0.09
    éĤĭ
    0.09
    Activations Density 0.046%

    No Known Activations