© 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. 55779
    Prev
    Next
    INDEX
    Explanations

    security services, roles, and practitioners

    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
    FORE
    -0.09
    reich
    -0.09
    ssi
    -0.09
    ä¼ĺçĤ¹
    -0.09
    ise
    -0.09
    ãģįãģ¡ãĤĵãģ¨
    -0.09
    ãģĵãģĵãģ¾ãģ§
    -0.08
    LEG
    -0.08
    累累
    -0.08
    akk
    -0.08
    POSITIVE LOGITS
    ties
    0.11
    -minded
    0.11
    .Cryptography
    0.10
    æĶ¸
    0.10
     conscious
    0.10
    ä¿Ŀåį«
    0.09
    åijĺ
    0.09
    tober
    0.09
     minded
    0.09
    -conscious
    0.09
    Activations Density 0.061%

    No Known Activations