© 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. 6347
    Prev
    Next
    INDEX
    Explanations

    ? followed by url parameters or xml

    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
    elling
    -0.09
     Barry
    -0.08
     arrang
    -0.08
    commons
    -0.07
     scor
    -0.06
     Fun
    -0.06
     deciding
    -0.06
    _https
    -0.06
    uchen
    -0.06
    ,e
    -0.06
    POSITIVE LOGITS
     Lump
    0.13
    :↵↵↵
    0.11
    /max
    0.11
    èIJ
    0.11
     Mobil
    0.11
    ?-
    0.10
     Lip
    0.10
     INCLUDED
    0.10
     Muj
    0.10
     Marker
    0.10
    Activations Density 0.007%

    No Known Activations