© 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. 33491
    Prev
    Next
    INDEX
    Explanations

    following "and" or parenthetical remarks

    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
    697
    -0.09
    (or
    -0.08
    —or
    -0.07
    IX
    -0.07
    —if
    -0.07
    ihar
    -0.07
    /reference
    -0.07
     Um
    -0.07
     Tou
    -0.07
     Sach
    -0.07
    POSITIVE LOGITS
     indeed
    0.17
     admittedly
    0.16
     certainly
    0.14
     please
    0.13
     I
    0.13
     arguably
    0.13
    inde
    0.12
     yes
    0.12
     frankly
    0.12
     thereby
    0.12
    Activations Density 0.166%

    No Known Activations