© 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. 90014
    Prev
    Next
    INDEX
    Explanations

    meaning and definition

    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
    ÑģÑĤи
    -0.08
     confl
    -0.08
     Panama
    -0.07
     sticky
    -0.07
    istes
    -0.06
     tid
    -0.06
     fencing
    -0.06
     forth
    -0.06
    "text
    -0.06
    EW
    -0.06
    POSITIVE LOGITS
    ilda
    0.12
     Trident
    0.11
     Mean
    0.11
     Trit
    0.11
     "><
    0.10
    Narrated
    0.10
    peng
    0.10
     gib
    0.10
    åĸ
    0.10
     CIM
    0.10
    Activations Density 0.142%

    No Known Activations