© 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. 117308
    Prev
    Next
    INDEX
    Explanations

    wide followed by descriptive terms

    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
     sever
    -0.08
    lint
    -0.08
     Proof
    -0.08
    aiser
    -0.08
    505
    -0.08
     Kaiser
    -0.08
     foo
    -0.08
    обÑĭ
    -0.07
     Obs
    -0.07
     competitiveness
    -0.07
    POSITIVE LOGITS
    -eyed
    0.19
     awake
    0.18
     open
    0.18
    -open
    0.17
     eyed
    0.16
    eyed
    0.15
     Awake
    0.14
     grin
    0.14
     apar
    0.14
    open
    0.14
    Activations Density 0.010%

    No Known Activations