© 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. 49940
    Prev
    Next
    INDEX
    Explanations

    list numbers followed by period

    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
     Lips
    -0.12
    IRR
    -0.11
     McConnell
    -0.11
     stal
    -0.11
    raf
    -0.11
    atu
    -0.10
    ersh
    -0.10
     Hatch
    -0.10
    enny
    -0.10
    gn
    -0.10
    POSITIVE LOGITS
     circ
    0.07
     earliest
    0.07
     Latin
    0.07
     cass
    0.07
     Cass
    0.07
     Hoe
    0.07
     Tex
    0.07
    —at
    0.07
     considerations
    0.06
     fours
    0.06
    Activations Density 0.059%

    No Known Activations