© 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. 4130
    Prev
    Next
    INDEX
    Explanations

    get in, down, back, up, out, off

    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
    uttle
    -0.09
    éºĪ
    -0.08
    æīĵä»Ĺ
    -0.08
    ä½łåĸľæ¬¢
    -0.08
    èĬ®
    -0.08
    åīĥ
    -0.08
    mute
    -0.08
    çľĭä¼¼
    -0.08
    ulen
    -0.08
    åĪĨåī²
    -0.08
    POSITIVE LOGITS
    iets
    0.09
    æĮ£
    0.09
    ç²Ĺ
    0.09
    æĴij
    0.09
    åĬ³åĬ¡
    0.09
     Budd
    0.08
    PrototypeOf
    0.08
    lá
    0.08
    gal
    0.08
    ç·£
    0.08
    Activations Density 0.081%

    No Known Activations