© 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. 115299
    Prev
    Next
    INDEX
    Explanations

    file 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
    [".
    -0.12
    UpDown
    -0.11
    akin
    -0.11
    Mirror
    -0.11
     saber
    -0.10
    Thrown
    -0.10
     Jah
    -0.10
     shuffle
    -0.10
     Chun
    -0.10
    atr
    -0.10
    POSITIVE LOGITS
     coinc
    0.08
     wee
    0.07
    ashi
    0.07
     snippet
    0.07
    opa
    0.07
     cuent
    0.07
     Paste
    0.06
     Eve
    0.06
    unsqueeze
    0.06
     Warren
    0.06
    Activations Density 0.012%

    No Known Activations