© 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. 112623
    Prev
    Next
    INDEX
    Explanations

    week, morning, day, Tuesday, afterwards

    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
     onstage
    -0.13
    zimmer
    -0.09
    pac
    -0.09
    endor
    -0.09
    imer
    -0.09
     everywhere
    -0.08
     outward
    -0.08
     Hull
    -0.08
     inward
    -0.08
    anel
    -0.08
    POSITIVE LOGITS
     to
    0.16
     armed
    0.16
     unarmed
    0.14
     ÑĩÑĤобÑĭ
    0.14
     Äijá»ĥ
    0.13
     ostensibly
    0.13
     afin
    0.13
     equipped
    0.13
     dressed
    0.12
    pend
    0.11
    Activations Density 0.307%

    No Known Activations