© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27478
    Prev
    Next
    INDEX
    Explanations

    need assistance with

    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
     earliest
    -0.11
    obl
    -0.10
     Boiler
    -0.10
    quil
    -0.10
    ere
    -0.10
    -boy
    -0.10
    gil
    -0.10
    aler
    -0.09
    gone
    -0.09
     NB
    -0.09
    POSITIVE LOGITS
    amp
    0.10
    eny
    0.08
    eda
    0.08
    ike
    0.08
    ija
    0.08
    izer
    0.08
    oth
    0.08
    anta
    0.08
    aggio
    0.07
    iel
    0.07
    Activations Density 1.403%

    No Known Activations