© 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. 14622
    Prev
    Next
    INDEX
    Explanations

    duksy

    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
     halt
    -0.09
    centers
    -0.08
    ÑģÑĤан
    -0.08
    igo
    -0.08
    à¹Ħ
    -0.08
     Spec
    -0.07
     plunge
    -0.07
    comed
    -0.07
    rip
    -0.07
    Center
    -0.07
    POSITIVE LOGITS
    DU
    0.13
    -du
    0.12
     duplication
    0.12
    PLICATE
    0.11
    ardin
    0.11
     Hast
    0.11
     dul
    0.11
     bist
    0.10
    eldorf
    0.10
     DU
    0.10
    Activations Density 0.073%

    No Known Activations