© 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. 26868
    Prev
    Next
    INDEX
    Explanations

    direction down

    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
    -down
    -0.19
     down
    -0.18
     Down
    -0.17
    down
    -0.16
    DOWN
    -0.16
     downwards
    -0.16
    Down
    -0.15
    _down
    -0.14
     DOWN
    -0.14
     downward
    -0.13
    POSITIVE LOGITS
    /up
    0.08
     cult
    0.08
     straw
    0.08
    ede
    0.08
    Ī
    0.08
     onto
    0.07
    eyJ
    0.07
     Carn
    0.07
    Anywhere
    0.07
     att
    0.07
    Activations Density 0.023%

    No Known Activations