© 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. 28201
    Prev
    Next
    INDEX
    Explanations

    exile, work, pursue, undertake

    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
     erfol
    -0.10
     Olsen
    -0.08
    ided
    -0.08
     befind
    -0.08
     Stay
    -0.08
     tav
    -0.08
     standby
    -0.08
    Stay
    -0.08
     Prest
    -0.08
    Marc
    -0.07
    POSITIVE LOGITS
    ãĤĴ
    0.14
    를
    0.13
     ãĤĴ
    0.13
     pursue
    0.11
     undertake
    0.11
    нÑĥÑİ
    0.11
     inst
    0.11
    ìĿĦ
    0.10
    zoek
    0.10
    ijo
    0.10
    Activations Density 0.398%

    No Known Activations