© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    best-game, fast-changing, long-term, award-winning, eye-catching

    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
     sized
    -0.18
     minded
    -0.17
     sided
    -0.14
     haired
    -0.13
     Sized
    -0.11
     eyed
    -0.10
     offs
    -0.09
     dimensional
    -0.09
     oriented
    -0.09
     related
    -0.07
    POSITIVE LOGITS
    -and
    0.27
    -of
    0.22
    -ever
    0.21
    -level
    0.19
    -to
    0.19
    -than
    0.19
    -through
    0.19
    -or
    0.18
    -quality
    0.18
    -specific
    0.18
    Activations Density 1.478%

    No Known Activations