© 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. 7631
    Prev
    Next
    INDEX
    Explanations

    ³³³ separator

    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
    ëĭ¹
    -0.08
     trail
    -0.08
     tense
    -0.08
    ------------
    -0.08
     safest
    -0.08
    trail
    -0.07
     flip
    -0.07
    Trail
    -0.07
     hang
    -0.07
    owl
    -0.07
    POSITIVE LOGITS
    ³³
    0.15
    ity
    0.14
    ::::::
    0.12
    itarian
    0.11
    lok
    0.11
    {text
    0.11
    mour
    0.11
    uvo
    0.11
    ilde
    0.10
    imits
    0.10
    Activations Density 0.017%

    No Known Activations