© 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. 31070
    Prev
    Next
    INDEX
    Explanations

    if followed by you or your

    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
    ensburg
    -0.11
    ruc
    -0.10
    velt
    -0.10
     Quar
    -0.10
    ück
    -0.10
     belonged
    -0.10
    enser
    -0.10
    porte
    -0.10
    <source
    -0.09
    /slick
    -0.09
    POSITIVE LOGITS
     there
    0.15
     your
    0.13
    there
    0.11
    your
    0.11
     ваÑĪ
    0.10
    feel
    0.10
     he
    0.10
    Your
    0.09
     after
    0.09
     There
    0.09
    Activations Density 0.090%

    No Known Activations