© 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. 30022
    Prev
    Next
    INDEX
    Explanations

    achieving results

    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
    ypad
    -0.10
     Claw
    -0.09
    Severity
    -0.08
     turning
    -0.08
     nasty
    -0.08
     severity
    -0.08
     giving
    -0.08
     Eg
    -0.08
     troubles
    -0.08
     lest
    -0.08
    POSITIVE LOGITS
     hopefully
    0.13
     evoke
    0.11
     proph
    0.11
     plaisir
    0.11
     desired
    0.11
     vic
    0.10
     provisional
    0.10
    ijn
    0.10
     proport
    0.10
     Hopefully
    0.10
    Activations Density 0.235%

    No Known Activations