© 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. 4832
    Prev
    Next
    INDEX
    Explanations

    passing information through parameters

    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
    éŨ
    -0.09
     fals
    -0.08
     Hart
    -0.08
     hart
    -0.08
     currencies
    -0.08
    abra
    -0.08
    jas
    -0.08
     Canc
    -0.08
     medal
    -0.08
    plat
    -0.08
    POSITIVE LOGITS
     handed
    0.28
     handing
    0.24
     passed
    0.21
    -pass
    0.20
     pass
    0.19
     passing
    0.19
     Passed
    0.18
     passes
    0.18
    pass
    0.17
    passed
    0.17
    Activations Density 0.084%

    No Known Activations