© 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. 28432
    Prev
    Next
    INDEX
    Explanations

    He, man, so, there

    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
     whatsoever
    -0.12
     dang
    -0.11
     myster
    -0.11
     extremely
    -0.10
     personally
    -0.10
     ðŁĺ
    -0.10
     absolutely
    -0.10
     thoroughly
    -0.09
     basically
    -0.09
     lightly
    -0.09
    POSITIVE LOGITS
     Afterwards
    0.12
     Him
    0.10
     uncomp
    0.09
     Mostly
    0.09
    Rep
    0.09
    .Maybe
    0.09
     Others
    0.09
    uele
    0.09
     Different
    0.09
    bw
    0.09
    Activations Density 0.045%

    No Known Activations