© 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. 15456
    Prev
    Next
    INDEX
    Explanations

    Leslie or lie followed by words

    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
    ÑĤе
    -0.10
    skins
    -0.10
     unw
    -0.09
    raphics
    -0.09
    istry
    -0.09
    erty
    -0.09
    lessly
    -0.09
     Hoch
    -0.09
    quake
    -0.09
     slight
    -0.08
    POSITIVE LOGITS
    ville
    0.09
    able
    0.09
    undra
    0.09
    ably
    0.09
    ÑİÑĤ
    0.09
    edly
    0.08
     Massive
    0.08
     wre
    0.08
     inverted
    0.08
    ableObject
    0.08
    Activations Density 0.118%

    No Known Activations