© 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. 112974
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    /native
    -0.10
     tamp
    -0.10
    æ®
    -0.09
    matter
    -0.09
     Native
    -0.09
    orage
    -0.09
     solitary
    -0.09
    _VF
    -0.09
     Matter
    -0.09
    -property
    -0.09
    POSITIVE LOGITS
    setattr
    0.08
    iec
    0.08
    EK
    0.08
    EUR
    0.08
    APO
    0.07
    cej
    0.07
    usting
    0.07
    inem
    0.07
     __(
    0.07
     Alle
    0.07
    Activations Density 0.410%

    No Known Activations