© 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. 55135
    Prev
    Next
    INDEX
    Explanations

    hallmark

    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
    ç½®æį¢
    -0.10
    ods
    -0.10
    lek
    -0.09
    æŁĶ
    -0.09
    æľī趣
    -0.09
    æ·ĺ
    -0.08
    ikes
    -0.08
    æĻ¤
    -0.08
    hev
    -0.08
    ernity
    -0.08
    POSITIVE LOGITS
    çī¹å¾ģ
    0.14
    æłĩå¿Ĺ
    0.13
     trademark
    0.12
     hallmark
    0.12
     characteristic
    0.12
    çī¹è´¨
    0.12
     signature
    0.12
    åķĨæłĩ
    0.11
    (signature
    0.11
    signature
    0.11
    Activations Density 0.074%

    No Known Activations