© 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. 16849
    Prev
    Next
    INDEX
    Explanations

    blocking access or pathways

    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
    chor
    -0.12
    alu
    -0.12
    ussen
    -0.11
    isl
    -0.11
    elden
    -0.11
    sst
    -0.11
    oggler
    -0.11
     Boyle
    -0.11
     blocks
    -0.11
    semb
    -0.11
    POSITIVE LOGITS
     access
    0.14
     paths
    0.13
    aded
    0.10
     pathways
    0.10
     out
    0.10
    ades
    0.09
     sunlight
    0.09
     path
    0.09
     pores
    0.08
     incoming
    0.08
    Activations Density 0.044%

    No Known Activations