© 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. 113486
    Prev
    Next
    INDEX
    Explanations

    Izuku, Izumi, Izmir, Izakaya

    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
    eval
    -0.11
    ijo
    -0.11
    ioms
    -0.11
    visor
    -0.11
    rogram
    -0.11
    eor
    -0.11
    ëĭ¹
    -0.10
     Armed
    -0.10
    iat
    -0.10
    eus
    -0.10
    POSITIVE LOGITS
     Candid
    0.08
    uren
    0.08
     Chronicles
    0.07
    hausen
    0.07
     camb
    0.07
     dimin
    0.07
     causal
    0.07
     Salon
    0.07
    č↵↵
    0.07
     Slam
    0.07
    Activations Density 0.003%

    No Known Activations