© 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. 29771
    Prev
    Next
    INDEX
    Explanations

    Heathrow, Heatherton, heathens

    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
    ing
    -0.11
    erus
    -0.10
    incare
    -0.09
    urgeon
    -0.09
     miracle
    -0.09
    论
    -0.09
    amac
    -0.09
    er
    -0.09
    -icon
    -0.09
     Miracle
    -0.09
    POSITIVE LOGITS
    field
    0.12
    arden
    0.10
    cock
    0.09
    OWN
    0.09
    ridge
    0.09
    cot
    0.09
    ey
    0.09
     catholic
    0.08
    fires
    0.08
     Heath
    0.08
    Activations Density 0.024%

    No Known Activations