© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    there be several

    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
     interdisciplinary
    -0.08
    éĴ
    -0.07
    ược
    -0.07
    usual
    -0.07
     your
    -0.07
    IPA
    -0.07
     Anal
    -0.07
     yours
    -0.07
     forward
    -0.07
    plemented
    -0.07
    POSITIVE LOGITS
     questions
    0.16
     fewer
    0.16
     doubts
    0.15
     several
    0.15
     other
    0.14
     many
    0.14
     no
    0.14
     inkl
    0.14
     few
    0.14
     tears
    0.14
    Activations Density 0.072%

    No Known Activations