© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87665
    Prev
    Next
    INDEX
    Explanations

    attributed speech reporting

    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
    Negative Logits
    /Dk
    -0.12
     restrictive
    -0.11
    -pos
    -0.11
     muse
    -0.11
     Willis
    -0.10
    ?↵↵↵↵↵↵
    -0.10
    ,ll
    -0.10
    msp
    -0.10
    Mont
    -0.10
    issen
    -0.10
    POSITIVE LOGITS
     replied
    0.09
     disclosed
    0.09
     utmost
    0.09
     Cabr
    0.08
     finally
    0.08
     cal
    0.08
     careless
    0.08
     participating
    0.08
     interfer
    0.08
     puck
    0.08
    Activations Density 0.031%

    No Known Activations