© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27122
    Prev
    Next
    INDEX
    Explanations

    Airport, Requirement, spaghetti dinner

    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
     Pref
    -0.08
     smear
    -0.07
     Blitz
    -0.07
    ẩu
    -0.07
     Barbie
    -0.07
    kur
    -0.07
     Elect
    -0.07
    OTH
    -0.07
    pref
    -0.07
    plex
    -0.06
    POSITIVE LOGITS
    {/
    0.12
     GRAT
    0.11
     rightly
    0.11
     redundant
    0.10
    eper
    0.10
    aben
    0.10
     singular
    0.10
    agnar
    0.10
     Stanton
    0.10
     improvised
    0.10
    Activations Density 0.012%

    No Known Activations