© 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. 112965
    Prev
    Next
    INDEX
    Explanations

    crow, crowds, crowell, crowne, crowding

    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
    ersion
    -0.09
     expectation
    -0.09
    orie
    -0.09
     Joint
    -0.08
    {}",
    -0.08
    ifr
    -0.08
    sert
    -0.08
    riz
    -0.08
     deflate
    -0.08
    erv
    -0.08
    POSITIVE LOGITS
     crow
    0.16
    ding
    0.13
     Crow
    0.13
    ning
    0.12
     crowded
    0.12
    der
    0.12
    e
    0.11
    df
    0.11
    bar
    0.11
    dl
    0.11
    Activations Density 0.005%

    No Known Activations