© 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. 58660
    Prev
    Next
    INDEX
    Explanations

    Francisco or Frisco

    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
    æŁĦ
    -0.09
    esser
    -0.09
    纪
    -0.09
    ica
    -0.09
    æĿŃ
    -0.09
    çłĶ究æīĢ
    -0.09
    aturas
    -0.08
     Trick
    -0.08
     Ging
    -0.08
    ativa
    -0.08
    POSITIVE LOGITS
    é©·
    0.10
    away
    0.10
    inct
    0.10
    éĻ²
    0.09
    -away
    0.09
    åŃIJéĩĮ
    0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.08
    led
    0.08
     oblig
    0.08
    æĻ¤
    0.08
    Activations Density 0.005%

    No Known Activations