© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27787
    Prev
    Next
    INDEX
    Explanations

    tubular extensions

    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
    à¸ĩ
    -0.13
    ably
    -0.11
    arily
    -0.11
    aylor
    -0.10
    cies
    -0.10
    oning
    -0.10
    ibly
    -0.10
    eer
    -0.10
    ÑĤа
    -0.10
    bones
    -0.10
    POSITIVE LOGITS
    ular
    0.16
    bing
    0.13
    bery
    0.11
    bers
    0.10
    let
    0.09
    lify
    0.09
    lets
    0.09
    pery
    0.09
    ules
    0.09
    ule
    0.09
    Activations Density 0.041%

    No Known Activations