© 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. 33085
    Prev
    Next
    INDEX
    Explanations

    Japanese names and titles

    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
     intros
    -0.10
     confrontation
    -0.09
     bö
    -0.09
     Stern
    -0.08
    (select
    -0.08
    cel
    -0.07
     Vanity
    -0.07
     interconnected
    -0.07
     Sands
    -0.07
    <|fim_middle|>
    -0.07
    POSITIVE LOGITS
     Wiki
    0.12
     wiki
    0.12
     unb
    0.10
     Wik
    0.10
     Synopsis
    0.10
    onna
    0.10
     discipl
    0.10
    issent
    0.10
     chapters
    0.10
     Nutzung
    0.09
    Activations Density 0.015%

    No Known Activations