© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63781
    Prev
    Next
    INDEX
    Explanations

    keychains, keychains, keys

    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
    åѤ
    -0.10
    éľľ
    -0.09
    åѤç«ĭ
    -0.09
    apat
    -0.09
    ooter
    -0.09
    ç§ģæľį
    -0.08
    æĢģ度
    -0.08
    éļĶ
    -0.08
    éĿ©
    -0.08
    ovi
    -0.08
    POSITIVE LOGITS
    ðŁĶij
    0.13
    /key
    0.12
    (Key
    0.12
    frames
    0.11
    afort
    0.10
    éĴ¥åĮĻ
    0.10
     Lime
    0.10
    (Keys
    0.10
    forge
    0.10
    cloak
    0.10
    Activations Density 0.096%

    No Known Activations