© 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. 28443
    Prev
    Next
    INDEX
    Explanations

    positive sentiment evaluation

    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
     personalised
    -0.10
    zas
    -0.10
    apus
    -0.10
    aab
    -0.10
     busiest
    -0.10
     unsupported
    -0.10
    fully
    -0.10
     bö
    -0.09
    iram
    -0.09
    veh
    -0.09
    POSITIVE LOGITS
     good
    0.36
     excellent
    0.29
     great
    0.25
    good
    0.24
     nice
    0.24
     effective
    0.22
     GOOD
    0.21
     better
    0.21
    好
    0.21
     useful
    0.20
    Activations Density 0.876%

    No Known Activations