© 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. 6953
    Prev
    Next
    INDEX
    Explanations

    H words, names, or initialisms

    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
    /header
    -0.12
     hollow
    -0.12
    hydro
    -0.12
     hardship
    -0.11
     humano
    -0.11
    horizontal
    -0.11
    orb
    -0.11
     hoodie
    -0.11
    /high
    -0.11
    hood
    -0.10
    POSITIVE LOGITS
    ERSHEY
    0.17
    archical
    0.17
    forth
    0.14
    ricane
    0.13
    ëĭ¹
    0.13
    quarters
    0.12
    essian
    0.11
    amient
    0.11
    icap
    0.11
    ricanes
    0.11
    Activations Density 2.219%

    No Known Activations