© 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. 55759
    Prev
    Next
    INDEX
    Explanations

    canine

    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
    land
    -0.10
    ighted
    -0.09
    ound
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    ero
    -0.09
    ders
    -0.09
     dint
    -0.09
    ouve
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    oused
    -0.08
    POSITIVE LOGITS
    ems
    0.11
    URES
    0.10
    人éĥ½
    0.09
    hood
    0.09
    .mas
    0.09
    cing
    0.09
    eur
    0.09
    yk
    0.08
    emente
    0.08
    龸
    0.08
    Activations Density 0.088%

    No Known Activations