© 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. 46434
    Prev
    Next
    INDEX
    Explanations

    R, P, C, A, b, ref

    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
    UGE
    -0.12
     NEG
    -0.11
    aura
    -0.10
    ë¡ľê·¸
    -0.10
    utr
    -0.10
    uge
    -0.10
     invit
    -0.10
     inout
    -0.10
     resemblance
    -0.10
     sost
    -0.10
    POSITIVE LOGITS
     antis
    0.09
     chiefly
    0.08
     apt
    0.08
    tes
    0.08
    eri
    0.08
     Checker
    0.08
    eds
    0.07
     smear
    0.07
     Gerard
    0.07
     bath
    0.07
    Activations Density 0.001%

    No Known Activations