© 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. 4872
    Prev
    Next
    INDEX
    Explanations

    particular or any

    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
     simpl
    -0.09
     rez
    -0.09
    alternative
    -0.09
    arse
    -0.08
    rese
    -0.08
    DEX
    -0.08
    Tem
    -0.08
     cur
    -0.08
    eba
    -0.08
    +"'
    -0.08
    POSITIVE LOGITS
     particular
    0.57
     specific
    0.54
    Specific
    0.47
    specific
    0.46
     Specific
    0.46
     PARTICULAR
    0.41
    _specific
    0.38
     specifically
    0.37
    pecific
    0.37
    -specific
    0.35
    Activations Density 0.254%

    No Known Activations