© 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. 48642
    Prev
    Next
    INDEX
    Explanations

    concentration, times, emitter, suppressed, extensions, structures

    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
     ostensibly
    -0.13
     ain
    -0.13
     folks
    -0.12
     frankly
    -0.12
     dude
    -0.12
     wanna
    -0.12
     decidedly
    -0.12
     dudes
    -0.12
     erst
    -0.11
     whence
    -0.11
    POSITIVE LOGITS
     Majority
    0.11
    sole
    0.10
    Liked
    0.10
     Unsure
    0.10
     entirety
    0.10
    Overall
    0.09
    odos
    0.09
    kea
    0.09
     filmer
    0.09
     Overall
    0.09
    Activations Density 0.132%

    No Known Activations