© 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. 16755
    Prev
    Next
    INDEX
    Explanations

    intensifier + positive sentiment

    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
    rup
    -0.12
    acco
    -0.11
    ABEL
    -0.11
    adora
    -0.11
    prox
    -0.11
    toi
    -0.10
     protagon
    -0.10
    emin
    -0.10
    onto
    -0.10
    /as
    -0.10
    POSITIVE LOGITS
     dislike
    0.12
     dread
    0.12
     hoped
    0.11
     hope
    0.11
     appreciate
    0.10
     respect
    0.09
     admire
    0.09
     doubted
    0.09
     sorry
    0.09
     forgive
    0.09
    Activations Density 0.040%

    No Known Activations