© 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. 112906
    Prev
    Next
    INDEX
    Explanations

    dev or Dev prefixes

    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
    entic
    -0.10
    ients
    -0.09
    emm
    -0.09
    /devices
    -0.09
    educt
    -0.09
    iente
    -0.09
    imd
    -0.08
    enna
    -0.08
    laden
    -0.08
    sic
    -0.08
    POSITIVE LOGITS
    ishly
    0.12
    iating
    0.11
    /null
    0.11
    /port
    0.11
    iation
    0.11
    oured
    0.11
    Ops
    0.10
     worsh
    0.10
    rait
    0.10
    yat
    0.10
    Activations Density 0.069%

    No Known Activations