© 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. 29974
    Prev
    Next
    INDEX
    Explanations

    text starting with д

    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
    haft
    -0.10
    غ
    -0.10
    ussen
    -0.10
     survivors
    -0.10
    ój
    -0.10
     Yus
    -0.09
    اÙģ
    -0.09
    __;
    -0.09
    ëĭ¹
    -0.09
     advertiser
    -0.09
    POSITIVE LOGITS
     cen
    0.08
    zp
    0.08
    toy
    0.08
    xr
    0.08
     collaps
    0.07
     Dixon
    0.07
    /script
    0.07
    uze
    0.07
    ipl
    0.07
     za
    0.07
    Activations Density 0.009%

    No Known Activations