© 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. 31052
    Prev
    Next
    INDEX
    Explanations

    Knocking!

    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
    æ¹Ł
    -0.08
    髦
    -0.08
    ä¹Ŀæ±Ł
    -0.08
    æ±
    -0.08
    æ³®
    -0.08
    бÑĭ
    -0.08
    æĶ¾åѦ
    -0.08
    ij
    -0.08
    lus
    -0.08
     Terr
    -0.08
    POSITIVE LOGITS
    æĪij说
    0.08
    à¹Ģà¸Ĺศ
    0.08
    ذا
    0.08
    滿
    0.08
    пÑĢавлен
    0.08
    .obtain
    0.08
    ;br
    0.08
    ä¸Ģæī¹
    0.08
    tempts
    0.08
    äºĨä¸Ģæī¹
    0.08
    Activations Density 0.520%

    No Known Activations