© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92263
    Prev
    Next
    INDEX
    Explanations

    incompatibility or unintended actions

    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
     od
    -0.12
     uncomfortable
    -0.11
    Noise
    -0.11
    gend
    -0.11
     mild
    -0.10
     comfortable
    -0.10
     Noise
    -0.10
     noise
    -0.10
    comfort
    -0.10
     singles
    -0.10
    POSITIVE LOGITS
     incompatible
    0.17
     compatibility
    0.15
     inadvert
    0.13
     inadvertently
    0.13
     unwitting
    0.13
    compat
    0.13
     Compatibility
    0.12
     unknow
    0.11
     mistakenly
    0.11
     compatible
    0.11
    Activations Density 0.217%

    No Known Activations