© 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. 112845
    Prev
    Next
    INDEX
    Explanations

    legal citations paragraph subsection

    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
     Daw
    -0.08
     hopeless
    -0.08
     regenerated
    -0.08
    js
    -0.08
    -only
    -0.08
     blind
    -0.08
     abstraction
    -0.07
     straw
    -0.07
    POSIT
    -0.07
     Hai
    -0.07
    POSITIVE LOGITS
     subparagraph
    0.17
    (b
    0.17
    (a
    0.17
    (ii
    0.15
    bis
    0.15
    iii
    0.15
     subsection
    0.14
    b
    0.14
    (iv
    0.14
    (c
    0.14
    Activations Density 0.868%

    No Known Activations