© 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. 49166
    Prev
    Next
    INDEX
    Explanations

    called

    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
     called
    -0.20
     termed
    -0.20
     Called
    -0.20
    Called
    -0.18
    called
    -0.17
    称
    -0.16
     dubbed
    -0.15
     titled
    -0.14
    -called
    -0.13
     referred
    -0.13
    POSITIVE LOGITS
     nond
    0.08
    SHORT
    0.08
     fasc
    0.08
    short
    0.08
     barg
    0.08
     grub
    0.07
    alian
    0.07
    icks
    0.07
    ordinal
    0.07
     heav
    0.07
    Activations Density 0.373%

    No Known Activations