© 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. 115714
    Prev
    Next
    INDEX
    Explanations

    Carl R. or Carl S

    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
     (::
    -0.11
    anse
    -0.10
    (::
    -0.10
    urge
    -0.10
    hos
    -0.10
     hust
    -0.09
    pis
    -0.09
    nte
    -0.09
    ngle
    -0.09
     precedence
    -0.09
    POSITIVE LOGITS
    Fatal
    0.09
    endor
    0.08
     mult
    0.08
     coc
    0.08
    ovich
    0.08
     link
    0.08
     lin
    0.08
     favor
    0.08
    ker
    0.08
    /testing
    0.08
    Activations Density 0.001%

    No Known Activations