© 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. 57832
    Prev
    Next
    INDEX
    Explanations

    different types or kinds

    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
    agus
    -0.09
    isphere
    -0.09
    ILES
    -0.08
    amp
    -0.08
    ä¸ĢæĿ¯
    -0.08
    iles
    -0.08
    ob
    -0.08
    æĪĸå¤ļ
    -0.08
    çĻ¾å®¶
    -0.08
    AMA
    -0.08
    POSITIVE LOGITS
    iating
    0.21
    ially
    0.16
    iates
    0.15
    iable
    0.14
    iability
    0.13
    iated
    0.13
    ç±»åŀĭçļĦ
    0.12
    iate
    0.12
    ials
    0.12
    åIJĦæł·
    0.12
    Activations Density 0.057%

    No Known Activations