© 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. 25307
    Prev
    Next
    INDEX
    Explanations

    Them

    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
    /her
    -0.08
    imos
    -0.07
    ADING
    -0.07
    ’
    -0.07
    orts
    -0.07
     Belle
    -0.07
    rams
    -0.07
    nts
    -0.07
     cris
    -0.07
    adero
    -0.06
    POSITIVE LOGITS
    efore
    0.15
    Them
    0.14
    atically
    0.14
     THEM
    0.13
    atisch
    0.12
    kur
    0.12
    damn
    0.12
    -IS
    0.11
     Cro
    0.11
     Them
    0.11
    Activations Density 0.031%

    No Known Activations