© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15999
    Prev
    Next
    INDEX
    Explanations

    lack of intent or interest

    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
     instantly
    -0.10
     forgiving
    -0.09
     immediately
    -0.09
     AUT
    -0.09
     dul
    -0.09
    ector
    -0.09
    IMS
    -0.09
     Baylor
    -0.09
    elay
    -0.09
     immediate
    -0.09
    POSITIVE LOGITS
     interest
    0.14
     anymore
    0.13
     bothering
    0.13
     bother
    0.12
    interest
    0.12
     bothered
    0.11
     Interest
    0.11
     fucks
    0.11
     listen
    0.11
    dra
    0.10
    Activations Density 0.029%

    No Known Activations