© 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. 31415
    Prev
    Next
    INDEX
    Explanations

    making or receiving calls

    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
     Erf
    -0.12
     propagated
    -0.11
    ünd
    -0.10
     FETCH
    -0.10
     Off
    -0.10
     indent
    -0.10
    IFO
    -0.10
     wartime
    -0.10
    nds
    -0.10
    /goto
    -0.10
    POSITIVE LOGITS
     caller
    0.20
     callers
    0.20
     sender
    0.17
     Caller
    0.16
     hangs
    0.16
     hang
    0.15
     fax
    0.15
    Caller
    0.15
     sending
    0.14
     send
    0.13
    Activations Density 0.102%

    No Known Activations