© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    (' followed by punctuation or word

    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
     Liter
    -0.11
     literally
    -0.10
    liter
    -0.10
    nest
    -0.08
     fancy
    -0.08
     Vall
    -0.08
     Dest
    -0.08
     vice
    -0.08
     fanc
    -0.08
     rasp
    -0.08
    POSITIVE LOGITS
     slang
    0.11
    atha
    0.11
    (hit
    0.10
    upe
    0.10
    ypes
    0.10
     BDSM
    0.09
     <|
    0.09
     irc
    0.09
     kort
    0.09
     infield
    0.09
    Activations Density 0.331%

    No Known Activations