© 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. 111811
    Prev
    Next
    INDEX
    Explanations

    tissue or issue + context

    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
    dish
    -0.12
    lit
    -0.11
    room
    -0.10
    erais
    -0.10
    ifiable
    -0.10
    /address
    -0.10
    lish
    -0.10
    lib
    -0.10
    anter
    -0.10
    /browse
    -0.10
    POSITIVE LOGITS
    /org
    0.17
     paper
    0.12
    -paper
    0.12
    /body
    0.10
    gne
    0.10
     Paper
    0.10
     damage
    0.10
    yte
    0.09
     mass
    0.09
    /cart
    0.08
    Activations Density 0.091%

    No Known Activations