© 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. 28452
    Prev
    Next
    INDEX
    Explanations

    ex- prefixes

    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
    isseur
    -0.10
    imento
    -0.09
    akening
    -0.09
    imenti
    -0.08
    riet
    -0.08
    tempts
    -0.08
    venes
    -0.08
    itionally
    -0.08
    stakes
    -0.08
     virtue
    -0.08
    POSITIVE LOGITS
    orc
    0.15
    posit
    0.15
    plan
    0.14
    clamation
    0.14
    fol
    0.14
     girlfriends
    0.14
    ynos
    0.14
     Mach
    0.14
    ogenous
    0.14
    tran
    0.13
    Activations Density 0.039%

    No Known Activations