© 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. 111864
    Prev
    Next
    INDEX
    Explanations

    no longer / gone / ceased

    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
     traditionally
    -0.13
     Trad
    -0.10
     finally
    -0.10
     ordinarily
    -0.09
     always
    -0.09
    olio
    -0.08
     suddenly
    -0.08
     normally
    -0.08
    Trad
    -0.08
     Always
    -0.08
    POSITIVE LOGITS
     anymore
    0.28
     Nowadays
    0.23
     nowadays
    0.23
     Gone
    0.21
     lost
    0.19
     ceased
    0.18
     changed
    0.17
     gone
    0.17
     replaced
    0.16
     resigned
    0.16
    Activations Density 0.220%

    No Known Activations