© 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. 47943
    Prev
    Next
    INDEX
    Explanations

    cost, cheaper, easier, simple

    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
     consegu
    -0.11
    @class
    -0.10
     consequential
    -0.10
     Classified
    -0.10
    ë³´
    -0.10
    yny
    -0.10
     Scotch
    -0.10
    icamente
    -0.10
    FFE
    -0.10
    installation
    -0.10
    POSITIVE LOGITS
     to
    0.11
     receiving
    0.10
    itten
    0.09
     groom
    0.08
    rio
    0.08
     participating
    0.08
     SMB
    0.08
    /li
    0.07
     Goodman
    0.07
     microwave
    0.07
    Activations Density 0.083%

    No Known Activations