© 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. 47436
    Prev
    Next
    INDEX
    Explanations

    report key, generation, card

    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
    -0.11
    itted
    -0.10
    thon
    -0.10
    hp
    -0.10
    hit
    -0.10
    vier
    -0.10
    åĻ¨
    -0.10
    onas
    -0.09
    pare
    -0.09
     Kel
    -0.09
    POSITIVE LOGITS
    edly
    0.20
    orial
    0.16
    ative
    0.13
    /report
    0.13
    oire
    0.12
     filed
    0.12
     report
    0.12
    (report
    0.11
     reports
    0.11
    .Report
    0.10
    Activations Density 0.097%

    No Known Activations