© 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. 50577
    Prev
    Next
    INDEX
    Explanations

    Lewis followed by names

    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
    еÑģÑĤв
    -0.08
    éħį
    -0.08
    ãĤģ
    -0.08
    itude
    -0.07
     capt
    -0.07
    Ĥ
    -0.07
    inya
    -0.07
    ITUDE
    -0.07
    Throwable
    -0.06
    lid
    -0.06
    POSITIVE LOGITS
    ohn
    0.20
    etta
    0.12
    brick
    0.12
    uhan
    0.11
    porte
    0.11
     tarn
    0.11
    hoff
    0.11
    olis
    0.11
    extr
    0.11
    orgen
    0.10
    Activations Density 0.014%

    No Known Activations