© 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. 4421
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
    IFO
    -0.12
     pf
    -0.12
     immediately
    -0.11
    ISCO
    -0.11
    !]
    -0.11
    .gs
    -0.11
    Terminate
    -0.11
     linger
    -0.11
    !(
    -0.11
     [("
    -0.11
    POSITIVE LOGITS
     softly
    0.11
     whispered
    0.10
    :↵↵
    0.08
     sotto
    0.08
     earnest
    0.08
     simply
    0.07
     soft
    0.07
     Bord
    0.07
     ironically
    0.07
     plainly
    0.07
    Activations Density 0.017%

    No Known Activations