© 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. 39138
    Prev
    Next
    INDEX
    Explanations

    subscribers and subscriber

    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
    ×ķת
    -0.11
    fern
    -0.09
    ä¾µçķ¥
    -0.09
    åŃĹ第
    -0.09
    æĤį
    -0.09
    ÙĪاÙĨ
    -0.09
    imps
    -0.09
    æ¶īåıĬåĪ°
    -0.09
    åłĨæĶ¾
    -0.09
     ë¶Ī구íķĺê³ł
    -0.08
    POSITIVE LOGITS
    hip
    0.12
    人家
    0.10
    ments
    0.09
    å¾Ĺèµ·
    0.09
    hips
    0.08
    ably
    0.08
    edImage
    0.08
    ãģĦãģŁãĤī
    0.08
    antha
    0.08
    hell
    0.08
    Activations Density 0.006%

    No Known Activations