© 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. 33562
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     savvy
    -0.12
     woes
    -0.12
     aficion
    -0.11
     quaint
    -0.11
     tantal
    -0.11
     Needless
    -0.10
     impeccable
    -0.10
     famed
    -0.10
     specs
    -0.10
     enlight
    -0.10
    POSITIVE LOGITS
     disproportionately
    0.15
     LGBTQ
    0.13
    âĢĮ
    0.13
     forcefully
    0.12
     prioritize
    0.12
     pornography
    0.12
     BDSM
    0.11
    Ă
    0.11
     oneself
    0.11
     transgender
    0.11
    Activations Density 0.926%

    No Known Activations