© 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. 7789
    Prev
    Next
    INDEX
    Explanations

    verbs describing actions or states

    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
     Mech
    -0.09
     rect
    -0.08
     proceeding
    -0.08
    RAP
    -0.08
     Mam
    -0.08
    bern
    -0.08
    erah
    -0.08
    fluence
    -0.08
     cleans
    -0.08
    quires
    -0.07
    POSITIVE LOGITS
     virtue
    0.13
     sheer
    0.13
    ening
    0.11
    sb
    0.11
    -products
    0.11
    gd
    0.11
    /rem
    0.10
     Bj
    0.10
    ifying
    0.10
     dint
    0.10
    Activations Density 0.262%

    No Known Activations