© 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. 115743
    Prev
    Next
    INDEX
    Explanations

    more specifically, precisely, actually

    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
    chk
    -0.08
    alin
    -0.08
    ican
    -0.08
    anz
    -0.07
    kok
    -0.07
     Ben
    -0.07
     massively
    -0.07
     spontaneously
    -0.07
    chin
    -0.07
    alian
    -0.07
    POSITIVE LOGITS
     sorry
    0.17
     technically
    0.16
     more
    0.15
     corrected
    0.15
     rather
    0.14
     realistically
    0.14
    Correction
    0.14
     Correction
    0.14
     actually
    0.14
     Actually
    0.13
    Activations Density 0.091%

    No Known Activations