© 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. 7800
    Prev
    Next
    INDEX
    Explanations

    best advice, money, analysis

    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
    wk
    -0.10
     Gord
    -0.10
    adb
    -0.10
     DF
    -0.10
    _Code
    -0.09
     imb
    -0.09
     Rudy
    -0.09
    nof
    -0.09
    ody
    -0.09
     ana
    -0.09
    POSITIVE LOGITS
     worst
    0.13
     Worst
    0.13
     worse
    0.13
    udd
    0.10
     Err
    0.10
     Budd
    0.09
    _below
    0.09
     worsening
    0.09
    urr
    0.09
     fanc
    0.09
    Activations Density 0.457%

    No Known Activations