© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    from the other end

    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
     Eck
    -0.10
    roker
    -0.09
    wit
    -0.09
     Oaks
    -0.09
    yahoo
    -0.09
    vip
    -0.08
    beautiful
    -0.08
    (vs
    -0.08
    *&
    -0.08
    rish
    -0.08
    POSITIVE LOGITS
     outside
    0.11
     trough
    0.10
     midpoint
    0.10
     bottom
    0.10
     lower
    0.10
    kes
    0.10
     lub
    0.09
     Outside
    0.09
     junction
    0.09
    å§ĭ
    0.09
    Activations Density 0.072%

    No Known Activations