© 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. 28539
    Prev
    Next
    INDEX
    Explanations

    options or alternatives

    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
    ouch
    -0.10
    _parallel
    -0.08
     dag
    -0.08
    errat
    -0.08
     slab
    -0.08
    315
    -0.08
    282
    -0.08
     Merry
    -0.08
     necessarily
    -0.07
     Patri
    -0.07
    POSITIVE LOGITS
     could
    0.19
    could
    0.17
     Could
    0.13
     Option
    0.13
     Alternatively
    0.13
     option
    0.13
     can
    0.12
     OR
    0.12
     мож
    0.12
    åı¯ä»¥
    0.12
    Activations Density 0.207%

    No Known Activations