© 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. 91241
    Prev
    Next
    INDEX
    Explanations

    names ending in ian or an

    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
     respondents
    -0.09
     Shelter
    -0.08
     poz
    -0.08
    PCS
    -0.07
     foot
    -0.07
    kiye
    -0.07
     preced
    -0.07
     Polo
    -0.07
     precedence
    -0.07
     Niet
    -0.07
    POSITIVE LOGITS
     Burl
    0.11
     Charge
    0.10
     severed
    0.10
    assen
    0.10
     cres
    0.10
    obsolete
    0.10
     constituent
    0.10
     reb
    0.10
     charge
    0.09
     mim
    0.09
    Activations Density 0.528%

    No Known Activations