© 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. 112376
    Prev
    Next
    INDEX
    Explanations

    Wil names

    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
    edly
    -0.13
    adel
    -0.09
    vale
    -0.09
    iola
    -0.09
    ¥
    -0.08
     revision
    -0.08
    osa
    -0.08
    yat
    -0.08
    enha
    -0.08
     Dillon
    -0.08
    POSITIVE LOGITS
    lem
    0.14
    lette
    0.11
    locks
    0.11
    hel
    0.11
    ber
    0.11
    kins
    0.10
    bert
    0.10
    lett
    0.10
     Emerging
    0.10
    comes
    0.10
    Activations Density 0.012%

    No Known Activations