© 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. 32285
    Prev
    Next
    INDEX
    Explanations

    harder, hard to

    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
    kul
    -0.11
    fad
    -0.10
    dia
    -0.09
    ptron
    -0.09
    bab
    -0.09
    serter
    -0.09
    ]|[
    -0.09
    _calendar
    -0.09
     Excellent
    -0.09
    kt
    -0.08
    POSITIVE LOGITS
    er
    0.50
    ened
    0.24
    ized
    0.21
    erate
    0.21
    erah
    0.20
    eria
    0.19
    ness
    0.19
    ly
    0.19
    erer
    0.19
    erin
    0.18
    Activations Density 0.022%

    No Known Activations