© 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. 26187
    Prev
    Next
    INDEX
    Explanations

    hard rock, facts, limit, proof

    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
    erro
    -0.09
     piercing
    -0.09
     tension
    -0.08
     flick
    -0.08
    lox
    -0.08
    ness
    -0.08
    ified
    -0.08
     discrim
    -0.08
    idan
    -0.08
     fren
    -0.08
    POSITIVE LOGITS
    -INF
    0.10
     splash
    0.10
    thora
    0.09
    ión
    0.09
    ÑģÑĤÑĢ
    0.09
     positions
    0.09
    TOT
    0.09
    prd
    0.09
    Hints
    0.09
    -hard
    0.09
    Activations Density 0.107%

    No Known Activations