© 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. 18137
    Prev
    Next
    INDEX
    Explanations

    fields and applications lists

    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
    achen
    -0.10
    bay
    -0.10
     Worlds
    -0.09
    edo
    -0.09
     Also
    -0.09
     cuer
    -0.09
    oyer
    -0.09
    Also
    -0.09
     also
    -0.09
     Amph
    -0.08
    POSITIVE LOGITS
     Lastly
    0.09
    awan
    0.09
     finally
    0.08
     Finally
    0.08
    iming
    0.08
    /or
    0.08
    ;-
    0.08
     McGu
    0.08
     Campo
    0.07
     GURL
    0.07
    Activations Density 0.389%

    No Known Activations