© 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. 46316
    Prev
    Next
    INDEX
    Explanations

    umlaut characters like ä followed by various endings

    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
     tandem
    -0.11
    s
    -0.10
    ngr
    -0.10
     attent
    -0.10
    qus
    -0.10
    sburg
    -0.09
    eldorf
    -0.09
    /self
    -0.09
    VAS
    -0.09
    UES
    -0.09
    POSITIVE LOGITS
    ät
    0.14
    är
    0.12
    rf
    0.10
    ytt
    0.10
     Gould
    0.10
    äd
    0.10
    iamo
    0.09
    rm
    0.09
    Ļ
    0.09
    buff
    0.09
    Activations Density 0.035%

    No Known Activations