© 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. 62126
    Prev
    Next
    INDEX
    Explanations

    game stats or metrics

    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
    伪
    -0.10
    å½ĵãģŁãĤĬ
    -0.09
    åħį责声æĺİ
    -0.09
    ä¸įæĩĤ
    -0.09
    å°Ķæĸ¯
    -0.09
    payer
    -0.09
    æĪij们å¿ħé¡»
    -0.08
    çģ¿
    -0.08
    éºĴ
    -0.08
    .github
    -0.08
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.10
    累积
    0.10
    累计
    0.10
    _PE
    0.09
    Ãłnh
    0.09
    åĨ°åĨ·
    0.09
    èī¯å¥½
    0.09
    积累äºĨ
    0.09
    สะสม
    0.09
    hang
    0.09
    Activations Density 0.039%

    No Known Activations