© 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. 18072
    Prev
    Next
    INDEX
    Explanations

    reported speech attribution

    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
     inv
    -0.08
     blinds
    -0.08
     aprove
    -0.08
     Wilde
    -0.08
    —he
    -0.08
     Cave
    -0.07
    /up
    -0.07
     blanks
    -0.07
     intimidate
    -0.07
     bars
    -0.07
    POSITIVE LOGITS
     said
    0.32
     says
    0.29
    said
    0.25
    says
    0.25
     exclaimed
    0.23
     Said
    0.22
     Says
    0.22
     say
    0.22
     replied
    0.18
     cried
    0.18
    Activations Density 0.118%

    No Known Activations