© 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. 57695
    Prev
    Next
    INDEX
    Explanations

    future role of

    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
    帻
    -0.09
     ----------------------------------------------------------------------↵
    -0.09
    ert
    -0.09
    åĮ¿åIJį
    -0.09
    å¾Īæ·±
    -0.09
    tober
    -0.09
    amar
    -0.09
    nee
    -0.08
    åħ¨æµģç¨ĭ
    -0.08
    rina
    -0.08
    POSITIVE LOGITS
    å±ķæľĽ
    0.11
     tense
    0.10
    ebin
    0.10
    çļĦæł·åŃIJ
    0.09
    ç¾İ好çĶŁæ´»
    0.08
    è¹ĭ
    0.08
    -thinking
    0.08
     Pros
    0.08
    åĺ±
    0.08
    ç¢Į
    0.08
    Activations Density 0.030%

    No Known Activations