© 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. 89340
    Prev
    Next
    INDEX
    Explanations

    names starting with P

    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
    ocket
    -0.12
    ictureBox
    -0.11
    iero
    -0.11
    aram
    -0.10
    ussy
    -0.10
    ause
    -0.10
    aste
    -0.10
    ako
    -0.10
    uzzle
    -0.10
    red
    -0.10
    POSITIVE LOGITS
    fen
    0.13
    fe
    0.13
    ek
    0.13
    iac
    0.12
    ined
    0.12
    hip
    0.12
    ech
    0.12
    fab
    0.11
    tas
    0.11
    uj
    0.11
    Activations Density 0.174%

    No Known Activations