© 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. 28276
    Prev
    Next
    INDEX
    Explanations

    when we consider

    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
     bu
    -0.06
    erti
    -0.06
     flick
    -0.06
    .key
    -0.06
    ä½Ļ
    -0.06
     QLD
    -0.06
     Ap
    -0.06
    udu
    -0.05
     Share
    -0.05
     eff
    -0.05
    POSITIVE LOGITS
     considering
    0.40
     consider
    0.34
    èĢĥ
    0.32
     Considering
    0.31
    consider
    0.31
     consid
    0.31
     consideration
    0.30
    Considering
    0.29
     considers
    0.29
     Consider
    0.28
    Activations Density 0.468%

    No Known Activations