© 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. 2905
    Prev
    Next
    INDEX
    Explanations

    locations and environments

    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
    æĪIJ为ä¸ĢåIJį
    -0.11
    ä¿ĥ使
    -0.10
    以èī²
    -0.09
    åĬ¨åijĺ
    -0.09
    æįŁå®³
    -0.09
    åıĹå½±åĵį
    -0.09
    éĤ¨
    -0.08
    çĤ
    -0.08
    çļĦ积æŀģæĢ§
    -0.08
    iens
    -0.08
    POSITIVE LOGITS
     midst
    0.10
     Rog
    0.10
    3
    0.10
     otherwise
    0.09
    ATURE
    0.09
    4
    0.09
    审æī¹
    0.09
    éļħ
    0.09
    oure
    0.09
    otherwise
    0.08
    Activations Density 0.087%

    No Known Activations