© 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. 88626
    Prev
    Next
    INDEX
    Explanations

    license headers and code formatting

    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
     conveying
    -0.11
     Harden
    -0.10
    erde
    -0.10
     telesc
    -0.10
     convey
    -0.10
    aname
    -0.10
     PURE
    -0.09
     hak
    -0.09
    steen
    -0.09
    %p
    -0.09
    POSITIVE LOGITS
    tha
    0.10
     tre
    0.09
     suspension
    0.08
     treasure
    0.08
    pla
    0.08
     RT
    0.08
     Chow
    0.08
     TRE
    0.08
     neutr
    0.08
     Southern
    0.08
    Activations Density 0.001%

    No Known Activations