© 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. 17771
    Prev
    Next
    INDEX
    Explanations

    so + state/feeling

    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
     Gio
    -0.11
    itty
    -0.10
     Bil
    -0.10
    olio
    -0.09
    ander
    -0.09
     brace
    -0.09
    amber
    -0.09
     mate
    -0.09
    +p
    -0.09
    idy
    -0.09
    POSITIVE LOGITS
     totally
    0.20
     NOT
    0.19
     Totally
    0.19
     definitely
    0.16
    tot
    0.14
    NOT
    0.13
     coolest
    0.13
     SO
    0.13
     soo
    0.13
    Tot
    0.13
    Activations Density 0.077%

    No Known Activations