© 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. 49625
    Prev
    Next
    INDEX
    Explanations

    classified into

    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
    bris
    -0.10
     Jub
    -0.10
    ál
    -0.09
    uros
    -0.09
    inski
    -0.09
     grounds
    -0.09
     á
    -0.09
    707
    -0.09
     scheduled
    -0.08
    rien
    -0.08
    POSITIVE LOGITS
     into
    0.23
    /class
    0.22
    into
    0.22
     Into
    0.21
    Into
    0.20
    _into
    0.19
     classify
    0.18
     categor
    0.18
     INTO
    0.17
     Classified
    0.15
    Activations Density 0.241%

    No Known Activations