© 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. 24963
    Prev
    Next
    INDEX
    Explanations

    content and related words

    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
    Tit
    -0.09
     intact
    -0.09
    ³
    -0.08
    pty
    -0.08
    reas
    -0.08
    coni
    -0.08
     Tit
    -0.08
     tit
    -0.08
    unk
    -0.07
     integrity
    -0.07
    POSITIVE LOGITS
    edly
    0.24
    ed
    0.22
    ment
    0.21
    edImage
    0.14
    iously
    0.13
    edd
    0.13
    ement
    0.13
    ieux
    0.12
    ration
    0.12
    ments
    0.12
    Activations Density 0.014%

    No Known Activations