© 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. 49174
    Prev
    Next
    INDEX
    Explanations

    dates with slashes /

    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
     unl
    -0.08
    CMP
    -0.07
     ul
    -0.07
     compound
    -0.07
     Pamela
    -0.07
     sil
    -0.07
     spin
    -0.07
    �t
    -0.07
     spl
    -0.07
    TM
    -0.07
    POSITIVE LOGITS
     Hawk
    0.13
    adors
    0.12
    zig
    0.11
    052
    0.11
     scaffold
    0.10
     Vern
    0.10
     Castillo
    0.10
    upro
    0.10
    elles
    0.10
    spath
    0.10
    Activations Density 0.001%

    No Known Activations