© 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. 29911
    Prev
    Next
    INDEX
    Explanations

    by followed by a name or entity

    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
    lep
    -0.10
    ilen
    -0.10
     scrutin
    -0.10
    fea
    -0.10
     briefed
    -0.09
    akin
    -0.09
     Fucked
    -0.09
     Masc
    -0.09
     Denis
    -0.09
     senior
    -0.09
    POSITIVE LOGITS
     Beautiful
    0.08
    (Resources
    0.08
     (/
    0.08
    Beautiful
    0.08
     beautiful
    0.07
    dv
    0.07
     vez
    0.07
    onn
    0.07
    INET
    0.07
     quarter
    0.07
    Activations Density 0.002%

    No Known Activations