© 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. 12226
    Prev
    Next
    INDEX
    Explanations

    moderator behavior

    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
    Negative Logits
    /her
    -0.10
    outh
    -0.09
    iness
    -0.09
    -0.09
    /be
    -0.09
    ery
    -0.09
    /or
    -0.08
    side
    -0.08
    pery
    -0.08
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    POSITIVE LOGITS
    edList
    0.13
    leur
    0.10
    иÑĢоваÑĤÑĮ
    0.10
    /mod
    0.10
     rÃłng
    0.10
    olu
    0.10
    æ´ĩ
    0.10
    å¦ģ
    0.09
    ares
    0.09
    yssey
    0.09
    Activations Density 0.011%

    No Known Activations