© 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. 115637
    Prev
    Next
    INDEX
    Explanations

    one thing

    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
     Ike
    -0.09
     longest
    -0.09
    aille
    -0.09
    ater
    -0.08
    addock
    -0.08
     Hell
    -0.08
     safest
    -0.08
    ân
    -0.08
    stead
    -0.07
    ideshow
    -0.07
    POSITIVE LOGITS
     definitely
    0.14
     noticeably
    0.14
     worth
    0.13
     particularly
    0.12
     noticed
    0.12
     NEVER
    0.12
    opi
    0.12
     common
    0.12
     commonly
    0.11
     guaranteed
    0.11
    Activations Density 0.036%

    No Known Activations