© 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. 111853
    Prev
    Next
    INDEX
    Explanations

    Them

    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
    òng
    -0.11
    prü
    -0.10
    cie
    -0.10
    alars
    -0.10
    keys
    -0.10
    EMA
    -0.10
     który
    -0.10
    way
    -0.10
     Buen
    -0.10
    ENDER
    -0.10
    POSITIVE LOGITS
    atically
    0.25
    /us
    0.25
     selves
    0.19
    /her
    0.17
    self
    0.17
    re
    0.17
    /we
    0.16
    elves
    0.16
    /th
    0.14
    're
    0.13
    Activations Density 0.070%

    No Known Activations