© 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. 6497
    Prev
    Next
    INDEX
    Explanations

    responsible for

    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
     acqu
    -0.09
     adorn
    -0.09
     Viv
    -0.09
     wink
    -0.09
     diam
    -0.09
     springs
    -0.08
    riv
    -0.08
     Pascal
    -0.08
    iliation
    -0.08
     counter
    -0.08
    POSITIVE LOGITS
     accountable
    0.17
    /account
    0.15
     Responsible
    0.13
     unto
    0.12
     responsible
    0.11
    onom
    0.11
     accountability
    0.11
     Accountability
    0.10
     Own
    0.10
     Sob
    0.09
    Activations Density 0.018%

    No Known Activations