© 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. 33298
    Prev
    Next
    INDEX
    Explanations

    I want to do it myself

    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
    aldi
    -0.11
    atte
    -0.10
     fantas
    -0.10
     Fav
    -0.10
     ratings
    -0.10
     Rating
    -0.10
     rating
    -0.10
    796
    -0.10
    quiv
    -0.10
     Ratings
    -0.10
    POSITIVE LOGITS
     insist
    0.25
     insisted
    0.24
     insisting
    0.22
     insists
    0.22
     insistence
    0.21
     stubborn
    0.18
     adamant
    0.14
     refusing
    0.13
     refused
    0.13
     pride
    0.13
    Activations Density 0.070%

    No Known Activations