© 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. 92295
    Prev
    Next
    INDEX
    Explanations

    middle parts and sections

    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
    Not in Any Lists

    No Comments

    Negative Logits
     undertaking
    -0.08
     Baxter
    -0.08
     Sit
    -0.08
    alla
    -0.07
     rigged
    -0.07
     Bes
    -0.07
     Corner
    -0.07
     Rig
    -0.07
     lon
    -0.07
     Ent
    -0.06
    POSITIVE LOGITS
     Unknown
    0.12
    line
    0.12
    Unknown
    0.12
    sections
    0.11
    /pub
    0.11
     unknown
    0.11
     gord
    0.11
     fronts
    0.11
     bodies
    0.11
    CCC
    0.11
    Activations Density 0.004%

    No Known Activations