© 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. 6501
    Prev
    Next
    INDEX
    Explanations

    urgent need or help

    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
    ech
    -0.10
     Mich
    -0.10
     membr
    -0.09
     Ga
    -0.09
    ich
    -0.09
     wrought
    -0.09
    Ga
    -0.09
     ech
    -0.09
     Stevens
    -0.09
    CHE
    -0.08
    POSITIVE LOGITS
     urgently
    0.25
     desperately
    0.22
     badly
    0.22
     ASAP
    0.18
     urgent
    0.16
     help
    0.15
     pronto
    0.13
     desper
    0.13
     assistance
    0.13
     Urg
    0.12
    Activations Density 0.175%

    No Known Activations