© 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. 116481
    Prev
    Next
    INDEX
    Explanations

    ans

    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
     shrinking
    -0.09
     bench
    -0.09
     Peg
    -0.09
    ntax
    -0.08
     shrink
    -0.08
    robat
    -0.08
    egan
    -0.08
     Holl
    -0.08
    thora
    -0.08
    lla
    -0.08
    POSITIVE LOGITS
    s
    0.16
    sen
    0.15
    -serif
    0.13
    ky
    0.13
    hu
    0.13
    o
    0.11
    h
    0.11
    sel
    0.11
    si
    0.11
    oftware
    0.11
    Activations Density 0.140%

    No Known Activations