© 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. 49882
    Prev
    Next
    INDEX
    Explanations

    go to

    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
    èĩªåıij
    -0.10
    aload
    -0.10
    å¢ĥ
    -0.10
    嶷
    -0.09
    端
    -0.09
    ç¾
    -0.09
    ä¸ĸ代
    -0.09
    à¹ģà¸Ł
    -0.09
    æ´»è·ĥ
    -0.08
    SizeMode
    -0.08
    POSITIVE LOGITS
    eam
    0.09
    éķ¿çĽ¸
    0.08
    illum
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
     Hoy
    0.08
    大éĻ¸
    0.08
    éĺħåİĨ
    0.08
    æķijåij½
    0.08
     вÑĭпÑĥÑģк
    0.08
    uition
    0.08
    Activations Density 0.020%

    No Known Activations