© 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. 33785
    Prev
    Next
    INDEX
    Explanations

    greater than or approximately

    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
    presso
    -0.10
    éļĽ
    -0.10
    éľŃ
    -0.10
    ниÑĩ
    -0.10
    endar
    -0.09
    anke
    -0.09
    tic
    -0.09
    éĻ¤å¤ĸ
    -0.09
    çѵ
    -0.09
    å¾ķ
    -0.09
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.10
     certain
    0.09
    rous
    0.09
    ä¸Ģå®ļ
    0.09
    ä¸Ģå®ļç¨ĭ度
    0.08
    æĪĸèĢħ
    0.08
    ormap
    0.08
    åľį
    0.08
    orp
    0.08
     or
    0.08
    Activations Density 0.105%

    No Known Activations