© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26920
    Prev
    Next
    INDEX
    Explanations

    special unicode characters

    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
     Caught
    -0.09
    mun
    -0.09
    acon
    -0.08
    prech
    -0.08
    atica
    -0.08
     pathetic
    -0.08
     Frid
    -0.08
     Ax
    -0.08
    spe
    -0.08
    ivas
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.40
    ï¸
    0.25
    âĢ
    0.14
     emoji
    0.11
     Bucks
    0.11
     Corm
    0.11
    empo
    0.10
    emoji
    0.10
    ated
    0.10
    ous
    0.10
    Activations Density 0.024%

    No Known Activations