© 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. 27660
    Prev
    Next
    INDEX
    Explanations

    800 numbers

    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
     Schl
    -0.08
     occasion
    -0.08
     sooner
    -0.07
    ÑģÑĭ
    -0.07
    fect
    -0.07
     aff
    -0.07
    arendra
    -0.07
    lok
    -0.07
    terr
    -0.07
     overt
    -0.07
    POSITIVE LOGITS
    assa
    0.11
     champ
    0.11
    /Dk
    0.11
    ivec
    0.11
    -flex
    0.11
    uite
    0.11
     delegate
    0.10
     slugg
    0.10
    lv
    0.10
     ,$
    0.10
    Activations Density 0.006%

    No Known Activations