© 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. 30313
    Prev
    Next
    INDEX
    Explanations

    companies and products

    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
     astounding
    -0.07
     proport
    -0.07
     startling
    -0.07
     behaviour
    -0.07
    quist
    -0.06
     foc
    -0.06
     colour
    -0.06
    <|fim_suffix|>
    -0.06
    imoto
    -0.06
    âĢ
    -0.06
    POSITIVE LOGITS
     folks
    0.14
     booze
    0.14
     staffers
    0.13
     info
    0.12
     aforementioned
    0.12
     youngsters
    0.12
     crappy
    0.12
     vibes
    0.12
     Sculpt
    0.12
     werd
    0.12
    Activations Density 0.617%

    No Known Activations