© 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. 111773
    Prev
    Next
    INDEX
    Explanations

    and much more

    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
     PARTICULAR
    -0.11
     counterpart
    -0.10
     Another
    -0.10
    "><!--
    -0.10
     Extra
    -0.09
    573
    -0.09
    rog
    -0.09
    /OR
    -0.09
     Fol
    -0.09
     jednak
    -0.09
    POSITIVE LOGITS
     more
    0.31
     much
    0.25
    more
    0.24
     MORE
    0.24
     More
    0.23
    More
    0.21
     MUCH
    0.20
     Much
    0.20
    -more
    0.20
    _more
    0.19
    Activations Density 0.099%

    No Known Activations