© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7093
    Prev
    Next
    INDEX
    Explanations

    informed commentary, choices, decisions, consent

    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
    odule
    -0.10
    åĩ¼
    -0.09
    åĽŀæĶ¶
    -0.08
    æĿ¡æ¬¾
    -0.08
     recovering
    -0.08
    åĨ¬
    -0.08
    recover
    -0.08
    ENSE
    -0.08
     tslib
    -0.08
     grades
    -0.08
    POSITIVE LOGITS
    çŁ¥æĥħ
    0.11
    èĨĽ
    0.10
    èĥ½åĬĽå¼º
    0.10
    вин
    0.10
    åŁºç¡Ģä¸Ĭ
    0.10
    ably
    0.09
    å¼Ĭ
    0.09
     BASIS
    0.09
    åĽ½æĥħ
    0.09
     unin
    0.09
    Activations Density 0.024%

    No Known Activations