© 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. 14779
    Prev
    Next
    INDEX
    Explanations

    separate and disconnect

    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
    raf
    -0.09
     consult
    -0.09
     breakthrough
    -0.09
    port
    -0.08
    yt
    -0.08
    rowsers
    -0.08
    oni
    -0.08
    ory
    -0.08
     bes
    -0.08
    bes
    -0.08
    POSITIVE LOGITS
     from
    0.23
     disconnect
    0.20
     detach
    0.19
     detachment
    0.18
     detached
    0.18
     disconnected
    0.17
    from
    0.17
     Disconnect
    0.17
    Detach
    0.17
     apart
    0.17
    Activations Density 0.147%

    No Known Activations