© 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. 32532
    Prev
    Next
    INDEX
    Explanations

    scientific or geographic names

    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¸ĢæŶ
    -0.10
    ä¼łç»Ł
    -0.10
    amble
    -0.09
     (++
    -0.09
    纤
    -0.09
    ä¸į平衡
    -0.09
    åħĪ导
    -0.09
    ä¸Ģéģį
    -0.08
    å¾ĹäºĨ
    -0.08
    /Framework
    -0.08
    POSITIVE LOGITS
    éĻ¢å£«
    0.10
    对åѦçĶŁ
    0.09
     Lent
    0.08
     Jr
    0.08
    æķĻæİĪ
    0.08
    åĪĨ管
    0.08
    èģĺ
    0.08
    utable
    0.08
    ount
    0.08
    oger
    0.07
    Activations Density 0.125%

    No Known Activations