© 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. 47036
    Prev
    Next
    INDEX
    Explanations

    demonstrate how it looks

    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
     superv
    -0.08
     shel
    -0.08
    slots
    -0.07
     postings
    -0.07
     outright
    -0.07
     stuff
    -0.07
    .fr
    -0.07
     nineteen
    -0.07
     precis
    -0.07
    -contact
    -0.07
    POSITIVE LOGITS
    isan
    0.13
    CDATA
    0.12
     Wend
    0.12
    atables
    0.11
     deber
    0.11
    indo
    0.11
     '*.
    0.11
    rts
    0.10
    Correction
    0.10
     sounding
    0.10
    Activations Density 0.001%

    No Known Activations