© 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. 22290
    Prev
    Next
    INDEX
    Explanations

    since [year]

    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
    ERS
    -0.11
    为ä»Ģä¹Īä¸į
    -0.10
    æľĢåĪĿ
    -0.10
    åŃIJå¼Ł
    -0.10
    æł¸åĩĨ
    -0.09
    ä¸Ģç±»
    -0.09
    Ñģоб
    -0.09
    èĢĦ
    -0.09
    former
    -0.09
    пÑĤ
    -0.09
    POSITIVE LOGITS
    俨
    0.08
    raq
    0.08
    itionally
    0.08
    ?page
    0.08
    åİ»è¿ĩ
    0.08
    pard
    0.08
    ively
    0.08
    -equiv
    0.07
    é½IJ
    0.07
    éĢıè¿ĩ
    0.07
    Activations Density 0.113%

    No Known Activations