© 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. 46552
    Prev
    Next
    INDEX
    Explanations

    expressing a mitigating positive

    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
     Chall
    -0.09
    ikh
    -0.09
    VK
    -0.08
     >>↵↵
    -0.08
     später
    -0.08
     BOTH
    -0.08
     sangat
    -0.08
     aud
    -0.08
    lli
    -0.08
     baj
    -0.08
    POSITIVE LOGITS
     atleast
    0.30
     thankfully
    0.24
     fortunately
    0.21
     luckily
    0.19
     albeit
    0.17
     consolation
    0.17
     redeem
    0.16
     Thankfully
    0.16
    èĩ³
    0.15
     least
    0.15
    Activations Density 0.168%

    No Known Activations