© 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. 18196
    Prev
    Next
    INDEX
    Explanations

    was/is/shall/may + verb/punctuation

    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
     besides
    -0.07
     multic
    -0.07
    oni
    -0.07
     outs
    -0.07
    '>↵↵
    -0.06
    oub
    -0.06
    776
    -0.06
    li
    -0.06
     Esk
    -0.06
     possible
    -0.06
    POSITIVE LOGITS
    plorer
    0.13
    ,Yes
    0.12
     Mic
    0.12
     Pars
    0.11
     nonetheless
    0.11
    992
    0.11
     Candle
    0.11
     Whisper
    0.11
     thereof
    0.11
    _si
    0.11
    Activations Density 0.045%

    No Known Activations