© 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. 39232
    Prev
    Next
    INDEX
    Explanations

    hoodie or hood

    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
    azon
    -0.09
    ozy
    -0.09
    æĦŁåıĹ
    -0.09
    éĴľ
    -0.09
    .opensource
    -0.09
    å¥Ī
    -0.09
    imates
    -0.08
    èĶļ
    -0.08
    端åįĪ
    -0.08
    xis
    -0.08
    POSITIVE LOGITS
    éĩįä¸Ńä¹ĭéĩį
    0.08
    æĪijä¸į
    0.08
    èµĦæľ¬
    0.08
     Ritch
    0.08
    çĮ¿
    0.08
    _dark
    0.08
    TypeInfo
    0.08
    åıĭåĸĦ
    0.08
     Capital
    0.08
    åħ¥åı£
    0.08
    Activations Density 0.002%

    No Known Activations