© 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. 112639
    Prev
    Next
    INDEX
    Explanations

    took over, trunk transmission, against a, stated an

    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
     frustrations
    -0.08
     shredd
    -0.08
    redo
    -0.07
     Lilly
    -0.07
     helicopt
    -0.07
     horrific
    -0.07
    (&
    -0.07
    FF
    -0.07
    uras
    -0.07
     frustrating
    -0.07
    POSITIVE LOGITS
     chiefly
    0.18
     smb
    0.17
     oneself
    0.17
     reckon
    0.17
     owing
    0.16
     reck
    0.13
     particulars
    0.13
     conspicuous
    0.12
     earnest
    0.12
     markedly
    0.12
    Activations Density 0.431%

    No Known Activations