© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    emergency helplines and phone numbers

    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
    ault
    -0.10
     Loren
    -0.09
     Hamm
    -0.09
     shouting
    -0.09
     scr
    -0.09
     gears
    -0.09
     pubs
    -0.09
    (Device
    -0.09
     íļĮ
    -0.09
     administration
    -0.09
    POSITIVE LOGITS
     hotline
    0.24
     hel
    0.21
     toll
    0.20
     call
    0.17
     Dial
    0.16
    -call
    0.16
    hel
    0.16
     emergency
    0.15
     dial
    0.15
     Hel
    0.15
    Activations Density 0.125%

    No Known Activations