© 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. 49354
    Prev
    Next
    INDEX
    Explanations

    introducing new information

    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
    asi
    -0.09
     theatrical
    -0.08
     NOT
    -0.08
     Do
    -0.08
    æ¥
    -0.08
    anni
    -0.07
     frog
    -0.07
    prefer
    -0.07
     mas
    -0.07
     sarÃł
    -0.07
    POSITIVE LOGITS
     read
    0.15
     suffice
    0.14
     reconsider
    0.14
     buckle
    0.13
     listen
    0.13
     wait
    0.13
     Picture
    0.12
     wÅĤa
    0.12
     let
    0.12
     check
    0.11
    Activations Density 0.050%

    No Known Activations