© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and codes

    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
    ione
    -0.10
    itta
    -0.08
    ocht
    -0.08
     Aux
    -0.08
     Swinger
    -0.08
     casts
    -0.08
    Vintage
    -0.08
     Rac
    -0.08
    âĢ°
    -0.08
    FML
    -0.08
    POSITIVE LOGITS
    è¿
    0.10
     hes
    0.10
    privileged
    0.10
     Hok
    0.09
     Bronx
    0.09
    chor
    0.09
    ASET
    0.09
     heir
    0.09
    hon
    0.09
    refund
    0.09
    Activations Density 0.772%

    No Known Activations