© 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. 63556
    Prev
    Next
    INDEX
    Explanations

    recommendations and suggestions

    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
    溯
    -0.09
    åıªéľĢ
    -0.09
    åŃº
    -0.09
    éĶĭ
    -0.09
    åıªéľĢè¦ģ
    -0.08
    çĥĻ
    -0.08
    ám
    -0.08
     synthetic
    -0.08
    夷
    -0.08
    äº¤æĽ¿
    -0.07
    POSITIVE LOGITS
    建议
    0.13
    èĩªæĦ¿
    0.13
    æľĢ好
    0.11
     hints
    0.11
    建èŃ°
    0.11
     strongly
    0.11
    æıIJ示
    0.10
    强çĥĪ
    0.10
    _hint
    0.10
    è¿Ļä¹Īåģļ
    0.10
    Activations Density 0.092%

    No Known Activations