© 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. 46558
    Prev
    Next
    INDEX
    Explanations

    the followed by noun/identifier

    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
     fray
    -0.10
     sake
    -0.09
     midst
    -0.08
     outset
    -0.08
     behalf
    -0.08
     whichever
    -0.07
     kinda
    -0.07
    quotes
    -0.07
     their
    -0.07
     the
    -0.07
    POSITIVE LOGITS
     chances
    0.19
     aim
    0.17
     emphasis
    0.17
     focus
    0.16
     result
    0.15
     entire
    0.14
    oret
    0.14
     presumption
    0.14
     tendency
    0.14
     goal
    0.14
    Activations Density 0.603%

    No Known Activations