© 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. 10702
    Prev
    Next
    INDEX
    Explanations

    meanwhile, followed by punctuation or specific words

    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
    mong
    -0.10
    or
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    ol
    -0.09
    è¿ĽèĢĮ
    -0.09
    è¿Ļä¹Ī说
    -0.09
     dabei
    -0.09
    佬
    -0.08
    itional
    -0.08
    _Framework
    -0.08
    POSITIVE LOGITS
    ellaneous
    0.10
    èįīæ¡Ī
    0.09
    forth
    0.09
    rd
    0.09
    мÑĥ
    0.08
    ÑĢ
    0.08
    Ùĥب
    0.08
    رÙĪ
    0.08
     IReadOnly
    0.08
    że
    0.08
    Activations Density 0.003%

    No Known Activations