© 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. 48102
    Prev
    Next
    INDEX
    Explanations

    people and scientific terms

    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
     tint
    -0.11
    iban
    -0.11
    vation
    -0.11
     Boca
    -0.10
     Swipe
    -0.10
     Vibr
    -0.10
     vagina
    -0.10
     Seks
    -0.10
    alties
    -0.10
    inidad
    -0.10
    POSITIVE LOGITS
     youth
    0.10
     Gef
    0.09
     couple
    0.09
     former
    0.09
     scientist
    0.09
     enorm
    0.08
     teens
    0.08
     college
    0.08
     middle
    0.08
     Harr
    0.08
    Activations Density 0.008%

    No Known Activations