© 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. 16906
    Prev
    Next
    INDEX
    Explanations

    also known as / called / involved

    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
     also
    -0.13
    also
    -0.11
    ä¹Ł
    -0.09
    son
    -0.08
    eka
    -0.08
     *
    -0.08
    gre
    -0.08
    cz
    -0.08
    ney
    -0.08
    aland
    -0.08
    POSITIVE LOGITS
    -r
    0.17
    ãģ¾ãģŁ
    0.13
    ë¡Ŀ
    0.12
     Trom
    0.11
     known
    0.11
     Männer
    0.10
     Known
    0.10
    -called
    0.10
     Lav
    0.10
     additionally
    0.10
    Activations Density 0.192%

    No Known Activations