© 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. 5848
    Prev
    Next
    INDEX
    Explanations

    but, effectiveness

    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
    zell
    -0.12
    ntl
    -0.11
     cog
    -0.11
    ucker
    -0.10
    antar
    -0.10
    weis
    -0.10
    enga
    -0.10
    .tf
    -0.10
     contrib
    -0.10
     picker
    -0.10
    POSITIVE LOGITS
     ineffective
    0.17
     effectiveness
    0.16
     uncovered
    0.14
     unprotected
    0.14
     unavoid
    0.12
     unrestricted
    0.12
     futile
    0.12
     peek
    0.12
     looph
    0.12
     leaks
    0.12
    Activations Density 0.196%

    No Known Activations