© 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. 16918
    Prev
    Next
    INDEX
    Explanations

    Immun, San, Indian, Spanish

    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
    "fmt
    -0.23
     Firefox
    -0.23
     Ùģ
    -0.21
     Fahrenheit
    -0.21
     feminism
    -0.20
     faculties
    -0.19
     fetus
    -0.19
     faculty
    -0.19
     fungi
    -0.19
     funeral
    -0.19
    POSITIVE LOGITS
    otes
    0.09
    /backend
    0.09
    .BackgroundColor
    0.08
    lname
    0.08
    .LastName
    0.08
    backward
    0.08
    <iostream
    0.08
    mother
    0.08
    nton
    0.08
    .cbo
    0.08
    Activations Density 2.442%

    No Known Activations