© 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. 34226
    Prev
    Next
    INDEX
    Explanations

    agree, approve, identify, appreciate

    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
     acknowledgment
    -0.11
     Representative
    -0.11
    efa
    -0.11
     acknowledgement
    -0.10
    vari
    -0.10
    öff
    -0.10
     overnight
    -0.10
    unic
    -0.10
     homage
    -0.10
    variably
    -0.10
    POSITIVE LOGITS
     strongly
    0.14
     personally
    0.11
     resonate
    0.11
    /em
    0.11
     fully
    0.10
    /res
    0.10
     greatly
    0.10
     closely
    0.10
     immensely
    0.10
     totally
    0.10
    Activations Density 0.023%

    No Known Activations