© 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. 26318
    Prev
    Next
    INDEX
    Explanations

    access control system

    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
     wrapping
    -0.11
     Extras
    -0.11
     extras
    -0.10
     rallying
    -0.09
     wrap
    -0.09
     copyright
    -0.09
     Kel
    -0.08
     flute
    -0.08
    /tool
    -0.08
     Marker
    -0.08
    POSITIVE LOGITS
     buz
    0.17
     remotely
    0.16
     buzz
    0.16
     gate
    0.14
     security
    0.13
     Gate
    0.13
     gates
    0.13
     CCTV
    0.12
     visitor
    0.12
     downstairs
    0.11
    Activations Density 0.020%

    No Known Activations