© 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. 25667
    Prev
    Next
    INDEX
    Explanations

    If there is

    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
     backgrounds
    -0.12
    :maj
    -0.12
     Mour
    -0.12
     Very
    -0.11
     оÑĩ
    -0.11
    lad
    -0.11
    icot
    -0.11
    />\
    -0.11
    ry
    -0.10
     excell
    -0.10
    POSITIVE LOGITS
     anywhere
    0.19
     anything
    0.17
    anything
    0.14
     ever
    0.13
    Anything
    0.11
     EVER
    0.11
     Anything
    0.11
    ught
    0.10
     ANY
    0.09
    Anywhere
    0.09
    Activations Density 0.051%

    No Known Activations