© 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. 28709
    Prev
    Next
    INDEX
    Explanations

    take for granted

    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
    éĩ
    -0.09
     Franken
    -0.08
     Tout
    -0.08
     unfore
    -0.07
     surprise
    -0.07
     Bison
    -0.07
     surprises
    -0.07
     dign
    -0.07
     dut
    -0.07
     unexpected
    -0.07
    POSITIVE LOGITS
     assumed
    0.17
     assumes
    0.15
     apprec
    0.14
     assumptions
    0.14
     assumption
    0.14
     freedoms
    0.14
     assume
    0.13
     assum
    0.13
     Apprec
    0.13
     conven
    0.13
    Activations Density 0.026%

    No Known Activations