© 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. 29303
    Prev
    Next
    INDEX
    Explanations

    case citations with numbers

    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
    @qq
    -0.15
     Flem
    -0.10
    extras
    -0.10
     forks
    -0.10
    abouts
    -0.10
     Fork
    -0.10
    .bg
    -0.09
    kke
    -0.09
    appers
    -0.09
     fork
    -0.09
    POSITIVE LOGITS
     bleed
    0.10
     bleeding
    0.10
    midd
    0.09
     camer
    0.08
    (en
    0.08
     imprint
    0.08
     èĭ
    0.08
     Reason
    0.08
     Complaint
    0.08
     Perry
    0.08
    Activations Density 0.541%

    No Known Activations