© 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. 6088
    Prev
    Next
    INDEX
    Explanations

    handheld devices, helm, reins

    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
    uali
    -0.12
     births
    -0.10
    ABB
    -0.09
    hill
    -0.09
    elib
    -0.09
     piled
    -0.09
     VIN
    -0.09
    dera
    -0.09
    lian
    -0.09
    DECL
    -0.09
    POSITIVE LOGITS
     powers
    0.13
     wield
    0.13
     authority
    0.13
     power
    0.11
    /display
    0.11
     talents
    0.10
     Pom
    0.10
     wielding
    0.10
    æĿĥ
    0.10
     expertise
    0.09
    Activations Density 0.006%

    No Known Activations