© 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. 50471
    Prev
    Next
    INDEX
    Explanations

    comma followed by a word

    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
     Lux
    -0.09
     Wit
    -0.08
     mega
    -0.08
    outers
    -0.08
     afford
    -0.07
    Behind
    -0.07
     hardware
    -0.07
     Positioned
    -0.07
    ulet
    -0.07
    ipe
    -0.07
    POSITIVE LOGITS
     BASIS
    0.12
    ses
    0.11
    lez
    0.11
     consecutive
    0.10
    fax
    0.10
    ifr
    0.10
     yc
    0.10
    .gif
    0.10
     Jed
    0.10
    wyn
    0.10
    Activations Density 0.001%

    No Known Activations