© 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. 89418
    Prev
    Next
    INDEX
    Explanations

    cookie consent and 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
     snapped
    -0.09
     mesa
    -0.09
    ellas
    -0.08
     gravy
    -0.08
     dok
    -0.08
     metaph
    -0.08
     Hyde
    -0.08
    serter
    -0.08
    ActionCode
    -0.08
    lever
    -0.08
    POSITIVE LOGITS
    .cookie
    0.14
     GDPR
    0.13
     Cookie
    0.12
     cookie
    0.12
    _cookie
    0.12
     Privacy
    0.11
    .Cookie
    0.11
    Privacy
    0.11
     COOKIE
    0.11
     Consent
    0.11
    Activations Density 0.577%

    No Known Activations