© 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. 27899
    Prev
    Next
    INDEX
    Explanations

    sodium, soda, sod

    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
    å§Ķåī¯ä¹¦è®°
    -0.10
    eler
    -0.10
    è¹ij
    -0.09
    ло
    -0.09
    á»ĩn
    -0.09
    ihan
    -0.08
    addon
    -0.08
     صÙģ
    -0.08
    /MIT
    -0.08
     Olympia
    -0.08
    POSITIVE LOGITS
    ãĤĿ
    0.09
    ÑĢÑĥж
    0.09
    ftware
    0.09
    zier
    0.09
    cul
    0.08
    çİij
    0.08
    brush
    0.08
    halb
    0.08
    iod
    0.08
    anch
    0.08
    Activations Density 0.010%

    No Known Activations