© 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. 88722
    Prev
    Next
    INDEX
    Explanations

    important to be careful

    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
    oland
    -0.12
    rts
    -0.12
    /port
    -0.11
    pery
    -0.11
     HALF
    -0.10
     sei
    -0.10
    vey
    -0.10
    yk
    -0.10
    ader
    -0.10
    /interfaces
    -0.10
    POSITIVE LOGITS
     vet
    0.11
     cautious
    0.11
     preca
    0.10
     vigilant
    0.10
     precautions
    0.10
     cautiously
    0.10
     caution
    0.10
     careful
    0.09
     precaution
    0.09
     prudent
    0.09
    Activations Density 0.001%

    No Known Activations