© 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. 59339
    Prev
    Next
    INDEX
    Explanations

    truth/true statements

    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
    å¿ĥ仪çļĦ
    -0.10
    ãĤ¯ãĥ©
    -0.09
    иÑĢÑĥ
    -0.09
    .binding
    -0.08
    æĦļ
    -0.08
    åħ¨éĿ¢å»ºæĪIJ
    -0.08
    å¿ĥ仪
    -0.08
    é¦ĸå¸Ń
    -0.08
    лÑİÑĩ
    -0.08
    强çĥĪçļĦ
    -0.08
    POSITIVE LOGITS
    å±ŀå®ŀ
    0.21
    æĺ¯çľŁçļĦ
    0.21
    羣å®ŀ
    0.20
     truth
    0.19
    äºĭå®ŀ
    0.19
    çľŁå¯¦
    0.18
     true
    0.18
    羣缸
    0.17
    true
    0.16
    羣å®ŀæĢ§
    0.15
    Activations Density 0.215%

    No Known Activations