© 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. 88531
    Prev
    Next
    INDEX
    Explanations

    <

    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
    >>>
    -0.12
    Potential
    -0.12
    Description
    -0.11
    Increase
    -0.11
    <<<<
    -0.11
    Pot
    -0.11
    <<<
    -0.10
    Nom
    -0.10
    -->↵
    -0.10
    Total
    -0.10
    POSITIVE LOGITS
    _<
    0.14
    +</
    0.13
    ...</
    0.12
    tf
    0.12
    ..<
    0.11
    _<?
    0.10
    è¯ķ
    0.09
    zac
    0.09
     detach
    0.09
    W
    0.09
    Activations Density 0.324%

    No Known Activations