© 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. 30733
    Prev
    Next
    INDEX
    Explanations

    negative experiences and abstract concepts

    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
    inspection
    -0.12
    ustralian
    -0.11
    aeda
    -0.10
    ubar
    -0.10
    ductive
    -0.09
    voie
    -0.09
    ients
    -0.09
    phans
    -0.09
    subclass
    -0.09
    gregate
    -0.09
    POSITIVE LOGITS
    gether
    0.35
    adecimal
    0.26
    evity
    0.26
    ductory
    0.25
    selling
    0.25
    jourd
    0.25
    theless
    0.25
    oretical
    0.24
    neath
    0.23
    existent
    0.23
    Activations Density 1.297%

    No Known Activations