© 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. 90369
    Prev
    Next
    INDEX
    Explanations

    _ /bits /browser Init Parameters

    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
    ÂŃt
    -0.08
    odom
    -0.07
    aec
    -0.07
    abd
    -0.07
    �t
    -0.07
    AQ
    -0.07
    uele
    -0.07
    425
    -0.07
    ETO
    -0.07
    CEF
    -0.07
    POSITIVE LOGITS
     volunte
    0.11
    <|endoftext|>
    0.11
     Georg
    0.10
     dbg
    0.10
    /card
    0.10
    iju
    0.10
    arkin
    0.10
     Mob
    0.10
     Tradable
    0.10
    _PM
    0.10
    Activations Density 0.251%

    No Known Activations