© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    social demands

    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
    comb
    -0.08
     Samp
    -0.07
    acher
    -0.07
     surely
    -0.07
     Bol
    -0.07
    olini
    -0.07
    licht
    -0.07
     seemingly
    -0.07
     Tess
    -0.07
    .lp
    -0.07
    POSITIVE LOGITS
     too
    0.22
     Too
    0.21
    Too
    0.20
    too
    0.18
     TOO
    0.16
    -too
    0.16
     insufficient
    0.12
    ukan
    0.12
    _TOO
    0.11
     demasi
    0.11
    Activations Density 0.042%

    No Known Activations