© 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. 55816
    Prev
    Next
    INDEX
    Explanations

    Beverly Hills

    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
    ãģĵãģ¨
    -0.09
    erval
    -0.09
     ÐĵÑĢ
    -0.09
    apel
    -0.09
    IJ
    -0.08
     Neck
    -0.08
    fires
    -0.08
    awesome
    -0.08
    ural
    -0.08
    ëłĪìĿ´
    -0.08
    POSITIVE LOGITS
    ment
    0.13
    ause
    0.12
    æĮŁ
    0.11
     Hills
    0.10
    çŀ©
    0.10
    รม
    0.10
    _HOOK
    0.09
     dÃłng
    0.09
    hus
    0.09
    tru
    0.09
    Activations Density 0.023%

    No Known Activations