© 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. 31152
    Prev
    Next
    INDEX
    Explanations

    HTML tags and documentation headers

    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
     Campos
    -0.11
    sti
    -0.08
     crap
    -0.08
     Nel
    -0.08
    ê¸
    -0.08
     backing
    -0.07
     fines
    -0.07
    /c
    -0.07
    î
    -0.07
    /to
    -0.07
    POSITIVE LOGITS
     lick
    0.11
    osi
    0.10
     Shepherd
    0.10
     âĢº
    0.10
    ocl
    0.10
     zaj
    0.10
     Jul
    0.10
    oji
    0.09
     denom
    0.09
    olar
    0.09
    Activations Density 0.110%

    No Known Activations