© 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. 111805
    Prev
    Next
    INDEX
    Explanations

    edges and boundaries

    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
     Nichols
    -0.11
     Ramp
    -0.09
     slowly
    -0.09
     Slow
    -0.09
     bolts
    -0.09
     BIG
    -0.09
     stride
    -0.08
     Slip
    -0.08
     slip
    -0.08
     ramp
    -0.08
    POSITIVE LOGITS
     Fully
    0.13
     deepest
    0.13
     fully
    0.13
     unreachable
    0.12
     gag
    0.11
    Fully
    0.11
     entirety
    0.11
     touching
    0.11
     bump
    0.11
     bottom
    0.11
    Activations Density 0.026%

    No Known Activations