© 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. 28128
    Prev
    Next
    INDEX
    Explanations

    css followed by styling terms

    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
    /LICENSE
    -0.10
    pects
    -0.09
    aller
    -0.09
    éĹº
    -0.09
    æ¦Ĩ
    -0.08
    çĿ¹
    -0.08
     illustr
    -0.08
    bons
    -0.08
    ogh
    -0.08
    WithError
    -0.08
    POSITIVE LOGITS
    ific
    0.08
    expo
    0.08
    3
    0.08
    ä¸īåįģå¹´
    0.08
    达人
    0.08
    oko
    0.08
    åľ£
    0.08
     Crafts
    0.08
    æŃ£å½ĵ
    0.08
    éĻ·éĺ±
    0.08
    Activations Density 0.101%

    No Known Activations