© 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. 10274
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    mal
    -0.10
    utes
    -0.08
    @stop
    -0.08
     ÐĽÐ¸
    -0.08
    sing
    -0.08
    涤
    -0.08
    æģ¨
    -0.08
    cial
    -0.08
    人为
    -0.08
    icamente
    -0.07
    POSITIVE LOGITS
    oram
    0.10
     пÑģ
    0.09
     Plays
    0.09
    éļıæŶéļıåľ°
    0.08
    èĻ½è¯´
    0.08
    éĻį临
    0.08
    平淡
    0.08
    InputDialog
    0.08
    åģİ
    0.08
    æľīç§į
    0.08
    Activations Density 0.734%

    No Known Activations