© 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. 4338
    Prev
    Next
    INDEX
    Explanations

    in the middle of

    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
    åľ¨
    -0.12
     in
    -0.11
     shores
    -0.11
     sides
    -0.11
     coastline
    -0.10
     therein
    -0.09
     shelves
    -0.09
     indoors
    -0.09
     در
    -0.09
     surfaces
    -0.09
    POSITIVE LOGITS
     midst
    0.28
     guise
    0.22
     nutshell
    0.21
     manner
    0.21
     vicinity
    0.20
     haste
    0.19
     hurry
    0.19
    /on
    0.18
     fashion
    0.17
     respects
    0.17
    Activations Density 4.782%

    No Known Activations