© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20281
    Prev
    Next
    INDEX
    Explanations

    text adventure

    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
     дÑĥÑħ
    -0.10
    ç¤ģ
    -0.09
    寨
    -0.09
     lax
    -0.09
    itized
    -0.08
    _outline
    -0.08
     ven
    -0.08
    å»ĵ
    -0.08
    ication
    -0.08
    reo
    -0.08
    POSITIVE LOGITS
    oji
    0.09
    .bootstrap
    0.09
    åĬ¡
    0.08
    вел
    0.08
     возд
    0.08
    é»ĺ
    0.08
    éĩĮçļĦ
    0.08
    åģļä¸įåĪ°
    0.08
    æī¹åıij
    0.08
    éĿł
    0.08
    Activations Density 0.007%

    No Known Activations