© 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. 6956
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and operations

    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
    ché
    -0.07
     cust
    -0.07
    ô
    -0.07
    ï¿
    -0.07
     tha
    -0.07
    atts
    -0.07
    -&
    -0.07
     indeb
    -0.07
     escalated
    -0.06
    udp
    -0.06
    POSITIVE LOGITS
     anti
    0.12
    anti
    0.12
    Anti
    0.11
     Anti
    0.11
    /features
    0.11
    <|endoftext|>
    0.11
    Interstitial
    0.11
    >Loading
    0.11
    aptcha
    0.11
    /gui
    0.11
    Activations Density 0.090%

    No Known Activations