© 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. 32969
    Prev
    Next
    INDEX
    Explanations

    new features:

    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
     Briggs
    -0.09
    ivo
    -0.08
    ensely
    -0.07
     Dor
    -0.07
    <|fim_middle|>
    -0.07
     frag
    -0.07
     dor
    -0.07
    iv
    -0.07
    LANG
    -0.07
    .photos
    -0.07
    POSITIVE LOGITS
     Below
    0.34
    Below
    0.31
     below
    0.30
     Let
    0.29
     let
    0.27
    Let
    0.26
     Read
    0.26
     Here
    0.24
     Lets
    0.24
     read
    0.24
    Activations Density 0.815%

    No Known Activations