© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60957
    Prev
    Next
    INDEX
    Explanations

    Jonathan or Dave followed by last names

    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
    uous
    -0.11
    ual
    -0.09
    Ø´Ùģ
    -0.09
    ĺ
    -0.09
    è¾ĥ好çļĦ
    -0.09
    å§Ķåijĺ
    -0.09
     quo
    -0.08
    åįģåĪĨ
    -0.08
    lessly
    -0.08
    lung
    -0.08
    POSITIVE LOGITS
    kü
    0.10
    åŃIJéĩĮ
    0.09
    媳
    0.09
    ì§ľ
    0.09
    apter
    0.09
    ells
    0.09
    iled
    0.09
    äºĨä»ĸçļĦ
    0.08
    ông
    0.08
    acket
    0.08
    Activations Density 0.077%

    No Known Activations