© 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. 112775
    Prev
    Next
    INDEX
    Explanations

    headed or drove to

    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
    uite
    -0.10
     simul
    -0.09
    inite
    -0.09
     Pare
    -0.09
     pare
    -0.09
    HM
    -0.09
     vil
    -0.09
    idot
    -0.09
     Meadow
    -0.08
    _far
    -0.08
    POSITIVE LOGITS
     locking
    0.10
    adas
    0.09
     unheard
    0.09
    esen
    0.09
     dès
    0.09
     downstairs
    0.09
     Tow
    0.09
    azi
    0.09
     hoping
    0.09
     calling
    0.08
    Activations Density 0.007%

    No Known Activations