© 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. 6740
    Prev
    Next
    INDEX
    Explanations

    still, nonetheless, nevertheless

    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
    kat
    -0.12
    agh
    -0.12
    ,eg
    -0.11
    Spr
    -0.11
    unto
    -0.10
    UNT
    -0.10
    _contin
    -0.10
     Contin
    -0.10
     Lab
    -0.10
    ocos
    -0.10
    POSITIVE LOGITS
     still
    0.79
     STILL
    0.72
     Still
    0.69
    still
    0.68
    Still
    0.65
     nonetheless
    0.63
     nevertheless
    0.62
    è¿ĺ
    0.47
     Nonetheless
    0.40
     stil
    0.40
    Activations Density 0.718%

    No Known Activations