© 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. 38705
    Prev
    Next
    INDEX
    Explanations

    wear and tear

    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
    失
    -0.10
    arine
    -0.09
    è¡Ļ
    -0.09
    embre
    -0.09
    ToLeft
    -0.09
    åºŁçī©
    -0.09
     ÐŃÑĤ
    -0.09
    éĤł
    -0.09
     tuner
    -0.09
    izin
    -0.09
    POSITIVE LOGITS
    åĬ¨çĶŁæĪIJ
    0.09
     Gow
    0.09
    asser
    0.08
    éľ²åĩº
    0.08
    ingly
    0.08
    iness
    0.08
    ìľ¨
    0.08
    ily
    0.08
    娩
    0.08
    anca
    0.08
    Activations Density 0.010%

    No Known Activations