© 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. 88664
    Prev
    Next
    INDEX
    Explanations

    without further ado, password, steps, bullet, time, wasting

    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
    uto
    -0.10
     yay
    -0.10
    astro
    -0.09
     WTF
    -0.09
    bil
    -0.09
    ceu
    -0.09
     emphasis
    -0.08
     PROVIDED
    -0.08
     Fitz
    -0.08
     forbid
    -0.08
    POSITIVE LOGITS
    hes
    0.14
     Lace
    0.11
     Singles
    0.10
    ,en
    0.10
    ingles
    0.10
     Nord
    0.09
     Dream
    0.09
     Nest
    0.09
    aat
    0.09
     dreaming
    0.09
    Activations Density 0.002%

    No Known Activations