© 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. 63512
    Prev
    Next
    INDEX
    Explanations

    Domonic Brown has

    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
    emble
    -0.09
    _TEAM
    -0.09
    asel
    -0.09
    éĺŁåijĺ们
    -0.09
    ç¾İåĮĸ
    -0.09
    (Paint
    -0.09
    -Version
    -0.08
    iphone
    -0.08
    æĻļå¹´
    -0.08
    aco
    -0.08
    POSITIVE LOGITS
    ado
    0.09
    uten
    0.09
     Nass
    0.09
    人æīį
    0.09
    éĢŁåº¦å¿«
    0.08
    grad
    0.08
    æĬ±
    0.08
    éľı
    0.08
    ige
    0.08
    ç¾Ķ
    0.08
    Activations Density 0.045%

    No Known Activations