© 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. 48366
    Prev
    Next
    INDEX
    Explanations

    stream/flow/string of

    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
     bounce
    -0.11
    ALA
    -0.11
    yle
    -0.11
     Wild
    -0.10
     collected
    -0.10
     Expansion
    -0.10
     scr
    -0.10
     grown
    -0.09
    ahr
    -0.09
    Wild
    -0.09
    POSITIVE LOGITS
     stream
    0.20
     flowing
    0.16
    stream
    0.16
    .Stream
    0.15
    (stream
    0.14
     continuous
    0.14
     flow
    0.14
     uninterrupted
    0.14
    -stream
    0.14
     flowed
    0.13
    Activations Density 0.051%

    No Known Activations