© 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. 49107
    Prev
    Next
    INDEX
    Explanations

    employed, result, capacity, capable

    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
     sinc
    -0.10
    @m
    -0.10
    ENC
    -0.10
     Humb
    -0.10
    gesch
    -0.09
    [..
    -0.09
    @c
    -0.09
    efa
    -0.09
    rone
    -0.09
    azio
    -0.09
    POSITIVE LOGITS
    anders
    0.08
    imson
    0.07
    Âł
    0.07
    /request
    0.07
    558
    0.07
    ÃĤ
    0.07
    /cal
    0.07
    irse
    0.07
    Pot
    0.07
     Pot
    0.06
    Activations Density 0.943%

    No Known Activations