© 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. 112722
    Prev
    Next
    INDEX
    Explanations

    first visit

    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
    an
    -0.08
     Jab
    -0.08
    tem
    -0.08
     touring
    -0.08
    stalk
    -0.08
     sm
    -0.07
     ses
    -0.07
     Natal
    -0.07
     Malone
    -0.07
     sk
    -0.07
    POSITIVE LOGITS
    Second
    0.11
     Second
    0.11
    _second
    0.11
    .Second
    0.10
     Secondly
    0.10
     Lump
    0.10
     junk
    0.10
    _SECOND
    0.10
     second
    0.09
    uve
    0.09
    Activations Density 0.295%

    No Known Activations