© 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. 6381
    Prev
    Next
    INDEX
    Explanations

    pygame, event, game

    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
    å³°
    -0.10
    æݨçIJĨ
    -0.09
    zon
    -0.09
    æ·ij
    -0.09
    寡
    -0.09
    å¥Ħ
    -0.09
    thon
    -0.08
     Pon
    -0.08
    åīľ
    -0.08
    anni
    -0.08
    POSITIVE LOGITS
    Pes
    0.09
     Baz
    0.09
    ruise
    0.09
    CDC
    0.08
    çĵ¦
    0.08
     AVR
    0.08
    æľ«
    0.08
    rän
    0.08
    makt
    0.08
    BUF
    0.08
    Activations Density 0.053%

    No Known Activations