© 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. 50457
    Prev
    Next
    INDEX
    Explanations

    need and wanting things

    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
     Gib
    -0.10
     overload
    -0.09
     Whenever
    -0.09
     Fauc
    -0.08
    inson
    -0.08
     Nic
    -0.08
    Sharper
    -0.08
     whenever
    -0.08
    ARS
    -0.08
     laz
    -0.08
    POSITIVE LOGITS
     desperately
    0.19
     desper
    0.16
     urgently
    0.14
     badly
    0.12
     dearly
    0.12
    ses
    0.11
     intact
    0.11
     continued
    0.11
     Dread
    0.10
     argent
    0.10
    Activations Density 0.125%

    No Known Activations