© 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. 33504
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     dagger
    -0.09
     persona
    -0.08
     Clarkson
    -0.08
     Cart
    -0.08
     educating
    -0.08
    qw
    -0.08
    .findIndex
    -0.08
    rec
    -0.08
     Dagger
    -0.08
     Merc
    -0.08
    POSITIVE LOGITS
    Terms
    0.13
     Terms
    0.12
     governing
    0.11
    /terms
    0.11
     Gover
    0.11
     terms
    0.11
     govern
    0.10
     Govern
    0.10
     troub
    0.10
     Complaint
    0.10
    Activations Density 0.062%

    No Known Activations