© 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. 5231
    Prev
    Next
    INDEX
    Explanations

    login to accounts

    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
     pies
    -0.12
    checksum
    -0.12
     TXT
    -0.11
    stick
    -0.11
    fillable
    -0.11
    izr
    -0.11
    azzi
    -0.11
     Flags
    -0.11
    reen
    -0.11
    /prom
    -0.11
    POSITIVE LOGITS
     accounts
    0.12
     account
    0.11
     computers
    0.10
     onto
    0.10
    iw
    0.08
     servers
    0.08
    kur
    0.08
     into
    0.07
     chat
    0.07
    accounts
    0.07
    Activations Density 0.095%

    No Known Activations