© 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. 30944
    Prev
    Next
    INDEX
    Explanations

    Nelson Tickets, Dark Thirty, punter

    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
    颤
    -0.10
    ç®±åŃIJ
    -0.10
    ä½ķåĨµ
    -0.09
    åı£ä¸Ń
    -0.09
    ä¸įéĶĪ
    -0.09
    çīº
    -0.09
    isi
    -0.09
    ä¸Ģ代
    -0.09
     GB
    -0.09
    rade
    -0.08
    POSITIVE LOGITS
    alis
    0.09
    æ²īè¿·
    0.09
    firm
    0.08
    æĴŃç§į
    0.08
    çĽijçĭ±
    0.08
    qml
    0.08
    dep
    0.08
    ä»ĺ
    0.08
     Bender
    0.08
    ovid
    0.08
    Activations Density 0.006%

    No Known Activations