© 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. 88718
    Prev
    Next
    INDEX
    Explanations

    ganja, Ganymede, Ganesha, gantry

    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
     Buen
    -0.11
     bust
    -0.11
     dyn
    -0.10
    905
    -0.10
     buses
    -0.10
    olv
    -0.10
    adoo
    -0.10
     trig
    -0.10
    _proc
    -0.10
     busted
    -0.10
    POSITIVE LOGITS
     vain
    0.08
     deceptive
    0.07
     disdain
    0.07
    jej
    0.07
     UNUSED
    0.07
    emet
    0.07
    nex
    0.07
     sequentially
    0.07
    eral
    0.07
    Clar
    0.07
    Activations Density 0.002%

    No Known Activations