© 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. 55042
    Prev
    Next
    INDEX
    Explanations

    SAS and Sar variants

    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¸įå¾Ĺä¸į说
    -0.10
    å·½
    -0.09
    ت
    -0.09
    kü
    -0.09
    weigh
    -0.09
    house
    -0.08
    thal
    -0.08
    sic
    -0.08
    ä¸įå¿ĺ
    -0.08
    éĨ®
    -0.08
    POSITIVE LOGITS
    æģŃæķ¬
    0.09
    çŨ
    0.09
    éĹ®åĢĻ
    0.09
    بد
    0.09
    masters
    0.09
    åĪ¶åĵģ
    0.08
    æ±²
    0.08
    ä¸ĭåİ»
    0.08
     unre
    0.08
    avana
    0.08
    Activations Density 0.022%

    No Known Activations