© 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. 30566
    Prev
    Next
    INDEX
    Explanations

    Isabella, Isosceles, Israel

    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
    haus
    -0.12
    Valid
    -0.11
    ients
    -0.10
    andan
    -0.09
    aning
    -0.09
    Active
    -0.08
    ski
    -0.08
    ез
    -0.08
    baum
    -0.08
    iper
    -0.08
    POSITIVE LOGITS
    rael
    0.22
    olation
    0.18
    olated
    0.16
    htar
    0.16
    LAND
    0.16
    otope
    0.16
    abella
    0.16
    lands
    0.15
    omorphic
    0.15
    abelle
    0.15
    Activations Density 0.277%

    No Known Activations