© 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. 17316
    Prev
    Next
    INDEX
    Explanations

    find something suitable

    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
     Cox
    -0.10
    atron
    -0.10
    adians
    -0.10
    hon
    -0.10
    996
    -0.10
    otch
    -0.10
     Cair
    -0.10
    397
    -0.10
     complexities
    -0.09
    orts
    -0.09
    POSITIVE LOGITS
     suitable
    0.16
     Suitable
    0.14
     reputable
    0.14
    /find
    0.13
     hidden
    0.12
     appropriate
    0.12
     trustworthy
    0.11
     reliable
    0.11
     Locate
    0.11
     locating
    0.11
    Activations Density 0.047%

    No Known Activations