© 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. 89856
    Prev
    Next
    INDEX
    Explanations

    phone/email/mail actions

    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
     incoming
    -0.10
     audition
    -0.10
     trap
    -0.09
     meeting
    -0.09
     traps
    -0.09
    anj
    -0.09
     bas
    -0.09
     responded
    -0.09
     Architect
    -0.09
    hdl
    -0.09
    POSITIVE LOGITS
     dial
    0.21
     Dial
    0.18
     contacts
    0.16
    .Dial
    0.16
     calling
    0.15
     dia
    0.15
     Contacts
    0.14
     misd
    0.14
     contact
    0.14
     phone
    0.14
    Activations Density 0.197%

    No Known Activations