© 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. 27880
    Prev
    Next
    INDEX
    Explanations

    again, rehabilitation

    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
    ilan
    -0.09
    rena
    -0.09
    /as
    -0.09
    noop
    -0.08
    é¦ĸ
    -0.08
     Maz
    -0.08
     Mens
    -0.08
     Instant
    -0.08
    IRA
    -0.08
    /+
    -0.08
    POSITIVE LOGITS
     stronger
    0.13
    areth
    0.12
     narrower
    0.11
    aug
    0.10
     smarter
    0.10
     NA
    0.10
     ea
    0.10
     harder
    0.10
     answering
    0.10
     weaker
    0.10
    Activations Density 0.015%

    No Known Activations