© 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. 47544
    Prev
    Next
    INDEX
    Explanations

    metal-on-metal

    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
    kre
    -0.11
    uffy
    -0.09
    SZ
    -0.09
     overlaps
    -0.09
    sha
    -0.09
    310
    -0.09
    alah
    -0.09
    vern
    -0.09
    FU
    -0.08
     refunds
    -0.08
    POSITIVE LOGITS
    /from
    0.11
     flesh
    0.10
     itself
    0.09
     pure
    0.09
     against
    0.09
     Lantern
    0.09
     wet
    0.09
     skin
    0.09
     Dank
    0.08
     Elder
    0.08
    Activations Density 0.025%

    No Known Activations