© 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. 10689
    Prev
    Next
    INDEX
    Explanations

    genus of

    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
    opia
    -0.10
    èĬĿ
    -0.08
    ondo
    -0.08
    两类
    -0.08
     bek
    -0.08
    acked
    -0.08
    ä¸ĢåĪĻ
    -0.08
    天使
    -0.08
    èĮ¬
    -0.08
    omers
    -0.08
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.10
    ë³Ħ
    0.09
    æĻĥ
    0.09
    è¡Ļ
    0.09
    _hdl
    0.09
    éĺIJ
    0.08
    ÑĦи
    0.08
    -wide
    0.08
    ishment
    0.08
    ç¿
    0.08
    Activations Density 0.098%

    No Known Activations