© 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. 25601
    Prev
    Next
    INDEX
    Explanations

    isaac, isaiah, izumi

    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
     romant
    -0.08
     Nam
    -0.08
    uve
    -0.08
    Nam
    -0.08
    tel
    -0.08
    tract
    -0.08
     dominated
    -0.08
     competit
    -0.08
     compét
    -0.08
    duct
    -0.07
    POSITIVE LOGITS
    rael
    0.13
    quierda
    0.13
    achsen
    0.12
    mail
    0.11
     Independ
    0.11
    quier
    0.11
    ockey
    0.10
    idor
    0.10
    meal
    0.10
    otope
    0.10
    Activations Density 0.089%

    No Known Activations