© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90736
    Prev
    Next
    INDEX
    Explanations

    plate, throw, like, temperature, cream, terms, division, oxide, Chief, analysis

    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
    nos
    -0.07
    /'+
    -0.07
    ï½ŀ
    -0.07
    ibr
    -0.07
     Hull
    -0.06
    cis
    -0.06
    ILLED
    -0.06
    comm
    -0.06
    uba
    -0.06
    ideo
    -0.06
    POSITIVE LOGITS
     HOWEVER
    0.11
    -wh
    0.10
     admittedly
    0.10
     Whit
    0.10
    caf
    0.09
     meld
    0.09
    .Areas
    0.09
     Whitney
    0.09
    -and
    0.09
    ificate
    0.09
    Activations Density 0.169%

    No Known Activations