© 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. 14834
    Prev
    Next
    INDEX
    Explanations

    names and associated contexts

    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
     fairly
    -0.10
     darn
    -0.09
     (*((
    -0.09
    ~
    -0.08
    (tm
    -0.08
     elo
    -0.08
     Stout
    -0.07
     McGill
    -0.07
     Wonderful
    -0.07
     pert
    -0.07
    POSITIVE LOGITS
    rone
    0.12
     xo
    0.11
    upe
    0.11
     highs
    0.11
    imity
    0.11
     scoreboard
    0.10
    erre
    0.10
     unh
    0.10
     ourselves
    0.10
    raj
    0.10
    Activations Density 0.028%

    No Known Activations