© 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. 47121
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast or qualification

    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
     Are
    -0.11
     Farrell
    -0.11
     unsure
    -0.11
     Might
    -0.11
    aggio
    -0.11
     maybe
    -0.11
     soll
    -0.11
    .NULL
    -0.11
    icut
    -0.11
     Maybe
    -0.11
    POSITIVE LOGITS
     clearly
    0.10
     suspect
    0.10
    Whatever
    0.09
     Clearly
    0.09
    rame
    0.09
     indis
    0.08
     felt
    0.08
    whatever
    0.08
     Whatever
    0.08
     whatever
    0.08
    Activations Density 0.039%

    No Known Activations