© 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. 6456
    Prev
    Next
    INDEX
    Explanations

    parts of things described

    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
    (detail
    -0.12
    -transparent
    -0.11
    -detail
    -0.11
     Ou
    -0.11
     intim
    -0.11
     insensitive
    -0.11
     CharSequence
    -0.10
     veil
    -0.10
    efore
    -0.10
     timetable
    -0.10
    POSITIVE LOGITS
     divided
    0.09
     Dillon
    0.09
     curved
    0.08
    eln
    0.08
    oin
    0.07
     RPM
    0.07
     generals
    0.07
     Omaha
    0.07
     Current
    0.07
     enclosing
    0.07
    Activations Density 0.010%

    No Known Activations