© 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. 115697
    Prev
    Next
    INDEX
    Explanations

    .aspx endings

    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
    .CO
    -0.10
    rego
    -0.10
     hur
    -0.10
    Leap
    -0.09
     Hur
    -0.09
    eree
    -0.09
    Ep
    -0.09
    enberg
    -0.09
    ervo
    -0.09
     hurry
    -0.09
    POSITIVE LOGITS
    POS
    0.08
     standard
    0.08
     behavioural
    0.08
     Bare
    0.08
     underscore
    0.08
     downgrade
    0.08
     quantitative
    0.08
    ellt
    0.08
     Ana
    0.07
    \:
    0.07
    Activations Density 0.001%

    No Known Activations