© 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. 112215
    Prev
    Next
    INDEX
    Explanations

    providing support or checks

    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
    urat
    -0.11
     Voll
    -0.10
    esk
    -0.10
    yx
    -0.10
     lon
    -0.10
    unner
    -0.09
     unveil
    -0.09
     filled
    -0.08
     vocab
    -0.08
    linger
    -0.08
    POSITIVE LOGITS
     provided
    0.15
     afforded
    0.14
     Provided
    0.13
    provided
    0.13
    /sources
    0.12
     external
    0.12
    ingly
    0.11
     PROVIDED
    0.11
     supplied
    0.10
    047
    0.10
    Activations Density 0.347%

    No Known Activations