© 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. 88891
    Prev
    Next
    INDEX
    Explanations

    old

    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
     sever
    -0.09
    cale
    -0.08
     behold
    -0.08
     alterations
    -0.08
     Nach
    -0.08
     Ach
    -0.08
    plural
    -0.08
    ĥĿ
    -0.08
     embell
    -0.08
     Unt
    -0.08
    POSITIVE LOGITS
    -fashioned
    0.19
    /new
    0.17
     fashioned
    0.16
     standby
    0.15
    /New
    0.15
    enburg
    0.14
    -school
    0.13
    (old
    0.11
    timer
    0.11
     (>
    0.11
    Activations Density 0.127%

    No Known Activations