© 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. 26109
    Prev
    Next
    INDEX
    Explanations

    sales or league

    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
    zel
    -0.09
     Venture
    -0.09
    rc
    -0.08
     dri
    -0.08
    atel
    -0.08
     contest
    -0.08
    oyer
    -0.07
     Ook
    -0.07
    Ign
    -0.07
    448
    -0.07
    POSITIVE LOGITS
    isser
    0.11
    Doctors
    0.11
    tram
    0.11
     Companion
    0.10
    è°
    0.10
    é»
    0.10
    çī
    0.10
    onde
    0.10
     doctors
    0.09
    ocity
    0.09
    Activations Density 0.001%

    No Known Activations