© 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. 88657
    Prev
    Next
    INDEX
    Explanations

    no matter what / not caring

    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
     via
    -0.08
     provoc
    -0.08
     administr
    -0.08
    215
    -0.08
     likely
    -0.07
     mark
    -0.07
     Via
    -0.07
     vigil
    -0.07
     dependence
    -0.07
     rightfully
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.12
    uden
    0.12
     WHATSOEVER
    0.12
    ofday
    0.12
    еб
    0.12
     Jeb
    0.11
     whether
    0.11
    ä½ķ
    0.11
    "&
    0.11
    æĺ¯åIJ¦
    0.11
    Activations Density 0.002%

    No Known Activations