© 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. 28916
    Prev
    Next
    INDEX
    Explanations

    en followed by j, ov, field, wood, berry

    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
    te
    -0.16
    er
    -0.15
    ten
    -0.14
    time
    -0.14
    tel
    -0.13
    gen
    -0.13
    gan
    -0.13
    den
    -0.12
    gun
    -0.12
    gui
    -0.12
    POSITIVE LOGITS
    esis
    0.21
    vironment
    0.19
    ning
    0.18
    bach
    0.16
    egal
    0.16
    jamin
    0.16
    ominator
    0.15
    etic
    0.15
    ews
    0.15
    ligne
    0.15
    Activations Density 0.568%

    No Known Activations