© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20271
    Prev
    Next
    INDEX
    Explanations

    actions and lists of items

    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
    ä¸įä»ħèĥ½
    -0.10
    å®ŀéĻħæĥħåĨµ
    -0.09
    æĪIJè´¥
    -0.08
    带åΰ
    -0.08
    åħĪæĺ¯
    -0.08
    第äºĮç§į
    -0.08
    æĭ³å¤´
    -0.08
    泪
    -0.08
    òng
    -0.08
    éĤ£æĹ¶åĢĻ
    -0.07
    POSITIVE LOGITS
    å¼Ģå±ķ
    0.11
    è··
    0.10
     sık
    0.10
    åļ¼
    0.10
    æľįåĬ¡ä¸Ńå¿ĥ
    0.10
    _oper
    0.09
    æıIJä¾Ľä¼ĺè´¨
    0.09
    æĭ¥æĬ±
    0.09
    éĸĭå±ķ
    0.09
     оÑģÑĥÑīеÑģÑĤвлÑı
    0.09
    Activations Density 0.135%

    No Known Activations