© 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. 63332
    Prev
    Next
    INDEX
    Explanations

    fulfillment 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
    ERING
    -0.10
    illing
    -0.10
    etheless
    -0.09
    LAN
    -0.09
    ised
    -0.09
    quiv
    -0.09
    ele
    -0.08
    ically
    -0.08
    ilo
    -0.08
    ampo
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.13
     Ñģобой
    0.11
    äºĨèĩªå·±çļĦ
    0.11
    大大å°ıå°ı
    0.10
    ICODE
    0.10
    aison
    0.10
    社ä¼ļ责任
    0.10
    ment
    0.09
    è¹Ī
    0.09
    箩
    0.09
    Activations Density 0.010%

    No Known Activations