© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    reported 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
     silence
    -0.11
    sil
    -0.11
     cite
    -0.11
     saying
    -0.10
     silent
    -0.10
    nak
    -0.10
     Roller
    -0.10
     tac
    -0.10
     mentioning
    -0.10
    ulta
    -0.10
    POSITIVE LOGITS
     æĸ
    0.09
     softly
    0.09
     monot
    0.08
     Salem
    0.08
    ordes
    0.08
    iped
    0.08
     rejo
    0.08
     urgently
    0.08
     elabor
    0.08
     Mend
    0.08
    Activations Density 0.114%

    No Known Activations