© 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. 47866
    Prev
    Next
    INDEX
    Explanations

    outflows and negative states

    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
     enough
    -0.11
    boys
    -0.10
    ser
    -0.10
    oser
    -0.09
    ness
    -0.09
     sera
    -0.09
     electricity
    -0.08
     wards
    -0.08
    otto
    -0.08
    oth
    -0.08
    POSITIVE LOGITS
    -clean
    0.12
    -strong
    0.11
     dunk
    0.11
     wet
    0.10
     mess
    0.10
     bele
    0.10
    ÙĪر
    0.10
     liv
    0.10
    -large
    0.10
    -before
    0.10
    Activations Density 0.001%

    No Known Activations