© 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. 32644
    Prev
    Next
    INDEX
    Explanations

    evidence and 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
     Ass
    -0.10
     muse
    -0.09
     bitterness
    -0.09
     dab
    -0.09
     blends
    -0.08
     Prism
    -0.08
     guesses
    -0.08
     privileged
    -0.08
    avr
    -0.08
     privilege
    -0.08
    POSITIVE LOGITS
     evidence
    0.55
     Evidence
    0.46
     proof
    0.46
    Evidence
    0.42
     evid
    0.42
     proofs
    0.37
     Proof
    0.35
    proof
    0.35
     incontro
    0.34
    è¯ģ
    0.33
    Activations Density 0.369%

    No Known Activations