© 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. 33351
    Prev
    Next
    INDEX
    Explanations

    processes involving time and stages

    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
    çĺ¾
    -0.09
    缨
    -0.08
    çļĦ巨大
    -0.08
    айн
    -0.08
    ä¸į让
    -0.08
    raquo
    -0.08
    ulent
    -0.08
    ä¸įåģľåľ°
    -0.08
    èĮ«èĮ«
    -0.08
    _SUS
    -0.08
    POSITIVE LOGITS
    èī¯
    0.12
    æ¶ĪåĮĸ
    0.10
    ä¸Ģ段æŶéĹ´
    0.10
    erot
    0.09
    äºĨä¸Ģä¼ļåĦ¿
    0.09
     Bow
    0.09
    èī¯æĢ§
    0.09
    illow
    0.09
     Kills
    0.09
    éĿĻ
    0.09
    Activations Density 0.022%

    No Known Activations