© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50897
    Prev
    Next
    INDEX
    Explanations

    palpation, palladium, pallor, palliative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Tw
    -0.07
     Shaman
    -0.07
    imm
    -0.07
     minimal
    -0.07
     tor
    -0.07
    ells
    -0.06
     conformity
    -0.06
    thon
    -0.06
    URE
    -0.06
     form
    -0.06
    POSITIVE LOGITS
     palp
    0.17
    able
    0.15
    ably
    0.13
     puls
    0.12
    abra
    0.12
    ability
    0.11
     sez
    0.11
     seiz
    0.11
     purs
    0.11
    ables
    0.11
    Activations Density 0.002%

    No Known Activations