© 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. 15463
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    zel
    -0.10
    sto
    -0.09
     Sto
    -0.09
    \:
    -0.08
     caret
    -0.08
     spiel
    -0.08
     clos
    -0.08
    aran
    -0.08
     Garrett
    -0.08
     unheard
    -0.08
    POSITIVE LOGITS
    -read
    0.14
     Read
    0.14
     read
    0.13
    Read
    0.13
    read
    0.11
    	Read
    0.11
    -analytics
    0.10
    (read
    0.10
     READ
    0.10
    _read
    0.10
    Activations Density 0.011%

    No Known Activations