© 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. 47740
    Prev
    Next
    INDEX
    Explanations

    availability and purchase status

    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
     Extr
    -0.10
     spender
    -0.10
     extr
    -0.10
    æĿ¡
    -0.10
    assin
    -0.09
     Ending
    -0.09
    usch
    -0.09
     infographic
    -0.08
    extr
    -0.08
     deferred
    -0.08
    POSITIVE LOGITS
     available
    0.40
     availability
    0.40
    available
    0.37
     Availability
    0.36
     Available
    0.34
    Availability
    0.33
    Available
    0.32
    -available
    0.32
     unavailable
    0.31
    availability
    0.30
    Activations Density 0.829%

    No Known Activations