© 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. 17053
    Prev
    Next
    INDEX
    Explanations

    also, bonus, or other languages

    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
     however
    -0.24
    however
    -0.19
     therefore
    -0.16
     nevertheless
    -0.16
     jedoch
    -0.14
     nonetheless
    -0.14
     meanwhile
    -0.14
     allerdings
    -0.13
    However
    -0.13
     thus
    -0.13
    POSITIVE LOGITS
     ALSO
    0.14
     also
    0.11
    bonus
    0.11
     bonus
    0.09
     también
    0.09
    also
    0.09
    erva
    0.09
     Bonus
    0.08
     financially
    0.08
     auch
    0.08
    Activations Density 0.191%

    No Known Activations