© 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. 88043
    Prev
    Next
    INDEX
    Explanations

    just, thanks, hope, still, be

    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
     retarded
    -0.10
     retard
    -0.10
     anew
    -0.09
     inval
    -0.09
     entirety
    -0.09
     Fucking
    -0.09
     FUCK
    -0.09
     nowrap
    -0.09
     idi
    -0.09
     cunt
    -0.09
    POSITIVE LOGITS
     naughty
    0.17
     darn
    0.17
     grandma
    0.16
     Grandma
    0.16
     proverb
    0.15
     pes
    0.15
     ðŁĺī↵↵
    0.14
     sweaty
    0.13
     fancy
    0.13
     dudes
    0.13
    Activations Density 1.170%

    No Known Activations