© 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. 30662
    Prev
    Next
    INDEX
    Explanations

    at risk

    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
     Replica
    -0.13
    ailed
    -0.12
    unge
    -0.12
    arih
    -0.12
    passed
    -0.11
    isch
    -0.11
     PRIV
    -0.11
    /pass
    -0.11
     dispatched
    -0.11
     Staples
    -0.11
    POSITIVE LOGITS
     Maur
    0.09
     submissions
    0.08
     Bos
    0.07
     pitches
    0.07
    hana
    0.07
    Submit
    0.07
    -/
    0.07
     mote
    0.06
     pitching
    0.06
     accused
    0.06
    Activations Density 0.002%

    No Known Activations