© 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. 56392
    Prev
    Next
    INDEX
    Explanations

    balanced

    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
    åŃº
    -0.10
    entes
    -0.09
    滨
    -0.09
    åĥ§
    -0.09
    çĦ¦
    -0.08
     Colbert
    -0.08
    龸
    -0.08
    æĪĸå°Ĩ
    -0.08
    å»ĵ
    -0.08
    伶
    -0.08
    POSITIVE LOGITS
    UDA
    0.11
    balanced
    0.10
     balanced
    0.10
    ness
    0.09
    åĿĩè¡¡
    0.09
    ầy
    0.09
     Balanced
    0.09
    оÑģÑĮ
    0.09
    (balance
    0.09
    ãĥIJãĥ©ãĥ³ãĤ¹
    0.08
    Activations Density 0.015%

    No Known Activations