© 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. 11184
    Prev
    Next
    INDEX
    Explanations

    bisexual, Mormon, .jboss

    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
    uper
    -0.09
    _scr
    -0.09
    _struct
    -0.09
    omens
    -0.09
     Mot
    -0.09
    umar
    -0.09
    UPER
    -0.08
    lem
    -0.08
    ley
    -0.08
    emens
    -0.08
    POSITIVE LOGITS
    踪
    0.09
    åĢĮ
    0.09
    osity
    0.09
    éħ±
    0.09
    亲æĥħ
    0.08
    icht
    0.08
    ä¸ĢæĹı
    0.08
    trie
    0.08
    åĨ³èĥľ
    0.08
    åIJ¸
    0.08
    Activations Density 0.004%

    No Known Activations