© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27282
    Prev
    Next
    INDEX
    Explanations

    adding an additional

    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
    mods
    -0.11
     Loc
    -0.11
    ENAME
    -0.10
    -Semit
    -0.09
    .tt
    -0.09
     welt
    -0.09
     Sharp
    -0.09
    cej
    -0.09
     petits
    -0.09
     Unter
    -0.08
    POSITIVE LOGITS
     minded
    0.09
     rem
    0.09
    Https
    0.09
     Sat
    0.08
     downwards
    0.08
    swick
    0.08
     overd
    0.08
    icky
    0.08
    bour
    0.08
     vit
    0.08
    Activations Density 0.457%

    No Known Activations