© 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. 39203
    Prev
    Next
    INDEX
    Explanations

    control over

    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
    便äºİ
    -0.09
    ersen
    -0.08
    æĹłæīĢ
    -0.08
    æ£ĵ
    -0.08
    çĽij
    -0.08
    wis
    -0.08
    ocs
    -0.08
    èµ·æĿ¥
    -0.08
    ARING
    -0.08
    æ£Ģå¯Łå®ĺ
    -0.08
    POSITIVE LOGITS
    çīº
    0.12
    èĪĽ
    0.11
    ending
    0.10
    å¾Īå¤ļäºĭæĥħ
    0.10
     ending
    0.10
    çŃīå¤ļ项
    0.09
    çºł
    0.09
    lus
    0.09
    iedade
    0.09
    èĽī
    0.09
    Activations Density 0.028%

    No Known Activations