© 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. 62408
    Prev
    Next
    INDEX
    Explanations

    some time ago

    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
    ä¸Ĭä¸ĭ
    -0.08
    iced
    -0.08
    emes
    -0.08
    REF
    -0.08
    éĻ¢éĻ¢éķ¿
    -0.08
    á»ħn
    -0.08
    غر
    -0.08
    iphy
    -0.08
    etti
    -0.08
    èĪª
    -0.08
    POSITIVE LOGITS
    åį°åº¦
    0.12
     India
    0.10
    India
    0.09
    æī¿
    0.09
    ãĤ¤ãĥ³ãĥī
    0.09
     Bangalore
    0.09
    éĩijå±±
    0.09
     Indian
    0.08
    ä¸įéĶĻ
    0.08
    çļĦè®¤çŁ¥
    0.08
    Activations Density 1.882%

    No Known Activations