© 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. 90957
    Prev
    Next
    INDEX
    Explanations

    snack or snacks

    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
    ed
    -0.11
    ossa
    -0.10
    zens
    -0.10
    acea
    -0.10
    capacity
    -0.10
    ight
    -0.10
    ocache
    -0.09
    ÑħÑĢан
    -0.09
     slack
    -0.09
    cession
    -0.09
    POSITIVE LOGITS
    nowled
    0.14
    enzie
    0.13
    intosh
    0.12
    t
    0.11
    ademic
    0.10
    istani
    0.10
    al
    0.10
    NOWLED
    0.10
    alon
    0.09
    ENA
    0.09
    Activations Density 0.031%

    No Known Activations