© 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. 32993
    Prev
    Next
    INDEX
    Explanations

    reporting or explaining events

    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
    arl
    -0.09
    zo
    -0.08
     Hum
    -0.08
    aq
    -0.08
    arlo
    -0.08
    azen
    -0.08
     thrott
    -0.08
     Cur
    -0.08
    immel
    -0.08
    atcher
    -0.08
    POSITIVE LOGITS
     kepada
    0.44
     to
    0.28
     unto
    0.24
    åĪ°
    0.23
     aloud
    0.19
    ç»Ļ
    0.19
     publicly
    0.18
    омÑĥ
    0.16
     aup
    0.16
    ToFile
    0.16
    Activations Density 1.321%

    No Known Activations