© 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. 16299
    Prev
    Next
    INDEX
    Explanations

    removable or easily attached/detached

    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
     Cobb
    -0.11
     refurbished
    -0.11
    ikon
    -0.10
    _exc
    -0.10
     buff
    -0.10
     Aber
    -0.10
     Jab
    -0.10
     Typed
    -0.10
     strained
    -0.09
     stal
    -0.09
    POSITIVE LOGITS
     removable
    0.37
     reversible
    0.28
     movable
    0.25
     easy
    0.25
     easily
    0.24
     adjustable
    0.24
     detach
    0.24
     Easily
    0.21
     convertible
    0.20
     easier
    0.20
    Activations Density 0.555%

    No Known Activations