© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14541
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    aland
    -0.10
    wig
    -0.09
    zik
    -0.09
    ando
    -0.08
    wel
    -0.08
     Petit
    -0.08
    arse
    -0.08
     Ged
    -0.08
    arks
    -0.08
    licit
    -0.08
    POSITIVE LOGITS
    -Americ
    0.09
    ka
    0.09
     Nich
    0.09
     quir
    0.09
     Kami
    0.08
    ...,
    0.08
     domin
    0.08
     vera
    0.08
     pins
    0.08
    oriously
    0.08
    Activations Density 0.001%

    No Known Activations