© 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. 90544
    Prev
    Next
    INDEX
    Explanations

    at this point

    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
     suddenly
    -0.12
     forall
    -0.10
     honeymoon
    -0.09
    Increased
    -0.09
     Suddenly
    -0.09
     eof
    -0.09
    Suddenly
    -0.09
    OUCH
    -0.09
    oba
    -0.09
     ordin
    -0.09
    POSITIVE LOGITS
     at
    0.19
     anymore
    0.19
     nowadays
    0.18
    At
    0.15
     honestly
    0.14
     At
    0.13
     tb
    0.13
    _at
    0.12
     preceded
    0.12
     Nowadays
    0.12
    Activations Density 0.122%

    No Known Activations