© 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. 32905
    Prev
    Next
    INDEX
    Explanations

    deeper, further, into

    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
    yn
    -0.10
     eternity
    -0.09
    eme
    -0.09
    ibern
    -0.09
     greeting
    -0.09
    ount
    -0.09
     readiness
    -0.09
     freight
    -0.09
     sudden
    -0.09
     extra
    -0.08
    POSITIVE LOGITS
     deep
    0.14
     deeper
    0.14
     tangled
    0.14
     spiral
    0.14
     intrigue
    0.13
     deepen
    0.13
     rabbit
    0.13
     obs
    0.12
     deepest
    0.12
     webs
    0.11
    Activations Density 0.001%

    No Known Activations