© 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. 29770
    Prev
    Next
    INDEX
    Explanations

    email address, web address, code

    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
    Subtitle
    -0.11
    leh
    -0.11
    subj
    -0.11
    ragen
    -0.11
    subtitle
    -0.10
    EntryPoint
    -0.10
    itre
    -0.10
     Deus
    -0.10
    .gg
    -0.10
    füh
    -0.10
    POSITIVE LOGITS
     anonymity
    0.09
    captcha
    0.09
     email
    0.09
     alphanumeric
    0.09
     automatically
    0.08
     anonymously
    0.08
     cookies
    0.08
     usted
    0.08
     consent
    0.08
     anonymous
    0.08
    Activations Density 0.330%

    No Known Activations