© 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. 114918
    Prev
    Next
    INDEX
    Explanations

    sign up or sign off

    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
     Laf
    -0.08
     chill
    -0.08
     Femme
    -0.08
     Ont
    -0.08
     cal
    -0.08
     Horny
    -0.08
     Suk
    -0.08
     calend
    -0.08
    inki
    -0.08
     SU
    -0.08
    POSITIVE LOGITS
    ups
    0.13
     unb
    0.12
    Ups
    0.11
    iswa
    0.11
    osis
    0.10
     ups
    0.10
     lik
    0.10
    offs
    0.10
    -ups
    0.10
     ver
    0.10
    Activations Density 0.002%

    No Known Activations