© 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. 46748
    Prev
    Next
    INDEX
    Explanations

    publisher's or employer's related information

    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
    iger
    -0.09
     comm
    -0.09
     pseud
    -0.09
    illac
    -0.08
    ary
    -0.08
     managerial
    -0.08
     Khal
    -0.08
     relative
    -0.08
    estr
    -0.08
    riel
    -0.07
    POSITIVE LOGITS
    ships
    0.15
     representatives
    0.13
    /provider
    0.13
    /vendor
    0.12
    ship
    0.11
    -sponsored
    0.11
     reps
    0.11
    -funded
    0.11
    -supported
    0.11
     Representatives
    0.11
    Activations Density 0.157%

    No Known Activations