© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31483
    Prev
    Next
    INDEX
    Explanations

    Rh followed by ona, ys, way, ymes, ODE, inos, oad, ubar

    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
    RESS
    -0.11
    ress
    -0.10
    fold
    -0.10
    ard
    -0.10
    rink
    -0.09
     organised
    -0.09
    rient
    -0.09
    acon
    -0.08
    oku
    -0.08
    enger
    -0.08
    POSITIVE LOGITS
    odium
    0.14
    oad
    0.13
    ymes
    0.13
    odes
    0.13
    ovan
    0.12
    azen
    0.12
    osg
    0.12
    azes
    0.12
    unan
    0.11
    ombo
    0.11
    Activations Density 0.010%

    No Known Activations