© 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. 6242
    Prev
    Next
    INDEX
    Explanations

    credit card details or phone numbers

    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
    craft
    -0.09
    bare
    -0.09
    ship
    -0.09
    286
    -0.09
    Cel
    -0.09
    bote
    -0.09
    wing
    -0.08
    unos
    -0.08
    boat
    -0.08
    bug
    -0.08
    POSITIVE LOGITS
    accessible
    0.09
     prowess
    0.09
     sleeves
    0.09
    RIX
    0.09
    rix
    0.09
    esser
    0.08
     Tommy
    0.08
    izz
    0.08
     riot
    0.08
    ovich
    0.08
    Activations Density 0.681%

    No Known Activations