© 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. 92090
    Prev
    Next
    INDEX
    Explanations

    review of evidence

    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
     tac
    -0.11
     Compact
    -0.09
    endale
    -0.09
     Tac
    -0.09
    ct
    -0.08
    rok
    -0.08
    Compact
    -0.08
    avel
    -0.08
    ey
    -0.08
     ast
    -0.08
    POSITIVE LOGITS
     rhetorical
    0.13
    .YesNo
    0.13
     ANSW
    0.12
    REET
    0.11
    .YES
    0.11
    iani
    0.10
     affirmative
    0.10
     Lifetime
    0.10
     Coff
    0.10
    BF
    0.10
    Activations Density 0.608%

    No Known Activations