© 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. 88856
    Prev
    Next
    INDEX
    Explanations

    font name, family, metrics, size

    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
     firmly
    -0.10
     Scre
    -0.10
     Hooks
    -0.09
     Wak
    -0.09
    alen
    -0.09
    enia
    -0.09
     seeded
    -0.08
    ubit
    -0.08
     Edgar
    -0.08
    rito
    -0.08
    POSITIVE LOGITS
    asso
    0.10
    engl
    0.10
     pudd
    0.09
     volunte
    0.09
     econom
    0.09
    -Ta
    0.09
     mouths
    0.09
     conspicuous
    0.09
    Č↵
    0.09
     irregular
    0.09
    Activations Density 0.005%

    No Known Activations