© 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. 17022
    Prev
    Next
    INDEX
    Explanations

    meet your needs

    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
     interacting
    -0.12
    aly
    -0.11
     surroundings
    -0.11
    eko
    -0.11
    веÑĢ
    -0.11
    its
    -0.10
     certainty
    -0.10
    innie
    -0.10
     Democracy
    -0.10
     ë°
    -0.10
    POSITIVE LOGITS
     whatever
    0.14
     your
    0.14
     desires
    0.12
     YOUR
    0.12
     any
    0.11
     emerg
    0.10
     every
    0.10
     needs
    0.09
     various
    0.09
     cravings
    0.09
    Activations Density 0.045%

    No Known Activations