© 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. 32310
    Prev
    Next
    INDEX
    Explanations

    qualifiers or exceptions

    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
     Lair
    -0.10
     Mood
    -0.09
     Mast
    -0.09
     Prof
    -0.09
    orry
    -0.09
    fec
    -0.09
    anic
    -0.08
    Misc
    -0.08
     urgently
    -0.08
     vi
    -0.08
    POSITIVE LOGITS
     barring
    0.14
    -ish
    0.12
    modulo
    0.12
     conditioned
    0.10
     partially
    0.10
     modulo
    0.10
    ish
    0.10
     SOME
    0.10
     semi
    0.10
     except
    0.10
    Activations Density 0.131%

    No Known Activations