© 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. 26410
    Prev
    Next
    INDEX
    Explanations

    optical, thermal, and 'mal' words

    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
    ðŁı»
    -0.12
    ðŁı½
    -0.09
    or
    -0.09
    ÙĤاÙĦ
    -0.09
    odian
    -0.09
    bies
    -0.09
    nis
    -0.08
    éĹ´çļĦ
    -0.08
    band
    -0.08
    ernet
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.10
    ãĤº
    0.09
    даÑĢ
    0.09
    亲çĪ±çļĦ
    0.09
    aleb
    0.09
    aison
    0.08
    æĦ§
    0.08
     undue
    0.08
    za
    0.08
    åī¯å±Ģéķ¿
    0.08
    Activations Density 0.032%

    No Known Activations