© 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. 57378
    Prev
    Next
    INDEX
    Explanations

    letters picked

    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
    åħĸ
    -0.10
    erguson
    -0.09
    -ish
    -0.09
    éķIJ
    -0.09
    èµ·çĤ¹
    -0.08
    slash
    -0.08
    åŀĵ
    -0.08
    ê°Ŀ
    -0.08
    TokenType
    -0.08
    amp
    -0.08
    POSITIVE LOGITS
    éĹ´çļĦ
    0.11
    æ¹ĸ
    0.10
    ä¸įåĩº
    0.10
    InThe
    0.09
    éķ¿æ±Ł
    0.09
    群éĩĮ
    0.09
    ç»ĦæĪIJçļĦ
    0.09
    ppo
    0.09
    owie
    0.09
    ì§ľ
    0.09
    Activations Density 0.448%

    No Known Activations