© 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. 30684
    Prev
    Next
    INDEX
    Explanations

    statement of opinion or situation

    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
     thereby
    -0.11
    611
    -0.08
     MC
    -0.08
    ull
    -0.07
     bran
    -0.07
    .eps
    -0.07
     Crosby
    -0.07
    ев
    -0.07
     SM
    -0.07
    .svg
    -0.07
    POSITIVE LOGITS
     So
    0.20
    So
    0.19
     prompting
    0.19
     so
    0.18
    æīĢ
    0.17
    	So
    0.16
    .So
    0.16
     decided
    0.15
    äºİ
    0.14
     prompts
    0.13
    Activations Density 0.491%

    No Known Activations