© 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. 91531
    Prev
    Next
    INDEX
    Explanations

    technical field introductions

    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
    —which
    -0.09
     vintage
    -0.08
     spit
    -0.07
     —
    -0.07
    —that
    -0.07
    —
    -0.07
     origins
    -0.07
    /license
    -0.07
     (âĪ
    -0.07
     Says
    -0.07
    POSITIVE LOGITS
    ³³³³³³³
    0.21
    ³³³³³³³³
    0.20
    ³³³³
    0.18
    ³³³
    0.15
    esson
    0.13
    ³³
    0.13
     Redistributions
    0.12
     Âł Âł
    0.12
    qus
    0.12
     utilise
    0.11
    Activations Density 0.063%

    No Known Activations