© 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. 6963
    Prev
    Next
    INDEX
    Explanations

    new things and concepts

    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
     pil
    -0.10
    irim
    -0.09
     double
    -0.09
    ihat
    -0.08
    ehen
    -0.08
     eagle
    -0.08
     spl
    -0.08
     tremend
    -0.08
    .di
    -0.08
    ADR
    -0.08
    POSITIVE LOGITS
     arrivals
    0.20
     arrival
    0.16
     occup
    0.15
     arriving
    0.14
     occupants
    0.14
     comer
    0.14
     arrives
    0.13
     ruling
    0.13
     arrived
    0.13
     arrive
    0.13
    Activations Density 0.066%

    No Known Activations