© 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. 29892
    Prev
    Next
    INDEX
    Explanations

    F. followed by numbers

    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
     pad
    -0.12
    vet
    -0.11
     associ
    -0.10
     contr
    -0.09
     warrant
    -0.09
     pads
    -0.08
     Pad
    -0.08
     dub
    -0.08
    pad
    -0.08
    LEV
    -0.08
    POSITIVE LOGITS
    irq
    0.12
     sens
    0.10
     essen
    0.09
     SHARES
    0.09
     Sens
    0.09
    commons
    0.09
     summed
    0.09
    dff
    0.09
    ittel
    0.09
    sst
    0.09
    Activations Density 0.711%

    No Known Activations