© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    Japanese names

    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
    nof
    -0.11
    side
    -0.10
    ÑģÑı
    -0.10
    letter
    -0.10
    SPATH
    -0.09
    edia
    -0.09
    sky
    -0.09
    STYPE
    -0.09
    heel
    -0.09
    ús
    -0.09
    POSITIVE LOGITS
    y
    0.15
    h
    0.13
    ro
    0.12
    hall
    0.11
    ences
    0.09
    eo
    0.09
    w
    0.09
     hinge
    0.08
    rov
    0.08
    rod
    0.08
    Activations Density 0.061%

    No Known Activations