© 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. 33489
    Prev
    Next
    INDEX
    Explanations

    staying in or at places

    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
    bcd
    -0.08
    ç«Ļ
    -0.08
     standing
    -0.08
     familiar
    -0.08
    TRS
    -0.08
     remain
    -0.08
     station
    -0.08
    -bl
    -0.08
     gd
    -0.07
     blij
    -0.07
    POSITIVE LOGITS
    cation
    0.16
     awhile
    0.13
    raud
    0.13
     longer
    0.12
     weekends
    0.11
     frag
    0.11
     tune
    0.11
     Frag
    0.11
    /host
    0.10
    veis
    0.10
    Activations Density 0.016%

    No Known Activations