© 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. 89671
    Prev
    Next
    INDEX
    Explanations

    this is

    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
     gem
    -0.10
     Bru
    -0.09
     either
    -0.08
     preferably
    -0.08
    ohl
    -0.08
     trib
    -0.08
     cent
    -0.08
     pearl
    -0.07
     slee
    -0.07
     whose
    -0.07
    POSITIVE LOGITS
     happened
    0.14
     happens
    0.13
     happen
    0.12
     causes
    0.12
     Happ
    0.11
     allows
    0.11
     leads
    0.11
     affects
    0.10
     enables
    0.10
    means
    0.10
    Activations Density 0.142%

    No Known Activations