© 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. 31615
    Prev
    Next
    INDEX
    Explanations

    sequence termination after License/Giants/fail/junction

    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
     envelopes
    -0.09
     Gust
    -0.09
     sheet
    -0.08
     scoring
    -0.08
     orth
    -0.08
     Buff
    -0.08
     Gus
    -0.08
     cas
    -0.07
     unh
    -0.07
    indow
    -0.07
    POSITIVE LOGITS
     Tail
    0.12
     swinging
    0.11
    /Math
    0.11
     Entries
    0.11
     Tenn
    0.11
     tail
    0.11
     swung
    0.11
     racer
    0.11
     Nylon
    0.10
     swing
    0.10
    Activations Density 0.008%

    No Known Activations