© 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. 29882
    Prev
    Next
    INDEX
    Explanations

    if...ed

    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
    i
    -0.15
    y
    -0.11
    ers
    -0.10
    àµįà´
    -0.10
    eut
    -0.09
    en
    -0.09
    ece
    -0.08
    ean
    -0.08
    /all
    -0.08
    eve
    -0.08
    POSITIVE LOGITS
    abeth
    0.12
    frage
    0.11
    ramework
    0.10
    uentes
    0.10
    ACS
    0.10
    forma
    0.10
     buzz
    0.10
    foon
    0.10
    flen
    0.10
    iram
    0.10
    Activations Density 0.040%

    No Known Activations