© 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. 56532
    Prev
    Next
    INDEX
    Explanations

    until now

    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¸Ģæīĭ
    -0.11
     //~
    -0.09
    å¾Īæ·±
    -0.09
    ä¸įçķĻ
    -0.08
    uro
    -0.08
    itaire
    -0.08
    ary
    -0.08
    åºĩ
    -0.08
    èĢĮä¸Ķ
    -0.08
    çĦ¦
    -0.08
    POSITIVE LOGITS
    缴åĪ°
    0.09
     вой
    0.08
    alta
    0.08
    æ³·
    0.08
    ìĤ¬ìĿ´
    0.08
    _ATTRIB
    0.08
    Unavailable
    0.08
    迪士尼
    0.08
    çĽĹçªĥ
    0.08
    elite
    0.08
    Activations Density 0.054%

    No Known Activations