© 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. 116732
    Prev
    Next
    INDEX
    Explanations

    from sites to sale

    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
    ymoon
    -0.11
    bx
    -0.11
    ah
    -0.09
     Dept
    -0.09
    Wrap
    -0.09
     Wr
    -0.09
     exceedingly
    -0.09
    ench
    -0.09
    tail
    -0.09
    Nation
    -0.09
    POSITIVE LOGITS
     designated
    0.14
     premises
    0.13
     predetermined
    0.11
     physical
    0.11
     preset
    0.10
     designate
    0.10
     Gum
    0.10
     storefront
    0.10
     specified
    0.10
    leon
    0.10
    Activations Density 0.021%

    No Known Activations