© 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. 30005
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    ADS
    -0.11
    reff
    -0.11
     Bart
    -0.11
    \:
    -0.11
     Kurt
    -0.10
     bart
    -0.10
    Walking
    -0.10
     freel
    -0.10
    abh
    -0.10
    bject
    -0.10
    POSITIVE LOGITS
     contro
    0.10
     coloured
    0.08
     Reeves
    0.08
     defy
    0.07
     bes
    0.07
     Harley
    0.07
     cont
    0.07
     cent
    0.07
    âĢ²
    0.06
    )&&
    0.06
    Activations Density 0.001%

    No Known Activations