© 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. 63485
    Prev
    Next
    INDEX
    Explanations

    existence or presence 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
    为åħ¶
    -0.11
     доб
    -0.10
    eddar
    -0.10
    æĺ¯ä»Ģä¹Īåij¢
    -0.10
    æŃ£éĿ¢
    -0.09
     ``(
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    беж
    -0.09
    çŃīåĪ°
    -0.09
    ãģªãĤīãģªãģĦ
    -0.09
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.10
    è¿ĻäºĽä¸ľè¥¿
    0.10
    agan
    0.10
    涯
    0.09
    æĦıåij³çĿĢ
    0.09
    _vc
    0.08
    çİ·
    0.08
     popular
    0.08
    æłĩå¿ĹçĿĢ
    0.08
    åŁł
    0.08
    Activations Density 0.200%

    No Known Activations