© 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. 112193
    Prev
    Next
    INDEX
    Explanations

    in + descriptor

    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
    arcy
    -0.08
     commitments
    -0.08
     familiar
    -0.07
    lys
    -0.07
    Increase
    -0.07
    /config
    -0.07
     correlations
    -0.07
     illusions
    -0.07
     Fre
    -0.07
    ARSE
    -0.07
    POSITIVE LOGITS
    sofar
    0.12
     appearance
    0.12
     both
    0.12
     scope
    0.11
     detail
    0.11
     nu
    0.11
     shape
    0.11
     their
    0.11
     purpose
    0.11
     size
    0.11
    Activations Density 0.120%

    No Known Activations