© 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. 88028
    Prev
    Next
    INDEX
    Explanations

    intensifiers and adjectives

    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
     Tim
    -0.09
     Cater
    -0.08
     Wel
    -0.07
     Carp
    -0.07
    unk
    -0.07
    op
    -0.07
    isto
    -0.07
    on
    -0.06
     Port
    -0.06
     fantastic
    -0.06
    POSITIVE LOGITS
     thereof
    0.12
    eam
    0.11
    /font
    0.11
    .cap
    0.11
    aved
    0.11
    cbd
    0.11
    /moment
    0.11
    igi
    0.10
    :{}
    0.10
    #undef
    0.10
    Activations Density 0.024%

    No Known Activations