© 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. 113064
    Prev
    Next
    INDEX
    Explanations

    anything

    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
     cigar
    -0.11
     Kam
    -0.10
     Fest
    -0.09
    wie
    -0.09
     cui
    -0.09
    edy
    -0.09
     miserable
    -0.08
    lius
    -0.08
     Manor
    -0.08
     counterpart
    -0.08
    POSITIVE LOGITS
     less
    0.12
     Dank
    0.10
    erver
    0.10
     gracious
    0.09
     EVER
    0.09
     interfering
    0.09
     regret
    0.09
     OU
    0.09
     LESS
    0.09
     suffice
    0.09
    Activations Density 0.007%

    No Known Activations