© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19698
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or 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
    رز
    -0.09
    è¿Ļä¸ĢåĪĩ
    -0.08
    ÅĪ
    -0.08
    thumb
    -0.08
    ilde
    -0.08
    á»±c
    -0.08
    éĻį
    -0.08
    _SPE
    -0.08
    stown
    -0.08
    åıĭ们
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ¥
    0.11
     respectively
    0.11
    åĪĨåĪ«
    0.11
    /or
    0.10
    澡
    0.09
     etc
    0.09
    åIJĦæľī
    0.09
    åĪĨåĪ«ä¸º
    0.09
    ãģ¨ãģĦãģ£ãģŁ
    0.09
    æ®ĸ
    0.09
    Activations Density 0.153%

    No Known Activations