© 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. 36857
    Prev
    Next
    INDEX
    Explanations

    Mark followed by a name or word

    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
    iliar
    -0.12
    ละ
    -0.10
    cribed
    -0.10
    udy
    -0.10
    ราà¸ĩ
    -0.09
    ecal
    -0.09
    ement
    -0.09
    cribe
    -0.08
    akh
    -0.08
    æĢª
    -0.08
    POSITIVE LOGITS
    edly
    0.11
    son
    0.10
    ov
    0.10
    ä½ĵ系建设
    0.10
    sson
    0.10
    é¬ĥ
    0.09
     bum
    0.09
    çļĦæ¯į亲
    0.09
    sville
    0.09
    ç¦ıéŁ³
    0.09
    Activations Density 0.015%

    No Known Activations