© 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. 49444
    Prev
    Next
    INDEX
    Explanations

    now what?

    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
    ddf
    -0.13
     outright
    -0.12
     alike
    -0.12
    Nom
    -0.12
    oste
    -0.12
    967
    -0.12
     Nom
    -0.11
    igg
    -0.11
    dda
    -0.11
     beforehand
    -0.11
    POSITIVE LOGITS
     Depends
    0.08
    (after
    0.07
    ry
    0.07
     huh
    0.07
     disg
    0.07
     depends
    0.07
    orias
    0.07
     Mag
    0.07
    IME
    0.07
     ?
    0.07
    Activations Density 0.029%

    No Known Activations