© 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. 112946
    Prev
    Next
    INDEX
    Explanations

    hybrid

    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
     genuinely
    -0.08
    reeze
    -0.08
    pd
    -0.07
    RAM
    -0.07
    spring
    -0.07
     head
    -0.07
    nts
    -0.07
     Sle
    -0.07
     collabor
    -0.07
     distinctive
    -0.07
    POSITIVE LOGITS
    ittal
    0.14
    acity
    0.13
    ging
    0.13
    ity
    0.12
    acious
    0.11
    иÑĦ
    0.11
    itated
    0.11
    zend
    0.11
    izada
    0.11
    ITT
    0.11
    Activations Density 0.013%

    No Known Activations