© 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. 25608
    Prev
    Next
    INDEX
    Explanations

    no denying or doubting

    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
    avy
    -0.11
     corruption
    -0.10
    izedName
    -0.09
    missive
    -0.09
    nip
    -0.09
     compliments
    -0.09
    Transient
    -0.09
    vox
    -0.09
     meas
    -0.09
     cleanly
    -0.09
    POSITIVE LOGITS
     need
    0.14
     reason
    0.14
     shame
    0.14
     guarantee
    0.13
     doubt
    0.12
     shortage
    0.12
     wrong
    0.12
    need
    0.12
     substitute
    0.11
     denying
    0.11
    Activations Density 0.042%

    No Known Activations