© 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. 46511
    Prev
    Next
    INDEX
    Explanations

    making calls or knocking

    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
    ieber
    -0.10
    agger
    -0.09
     BODY
    -0.09
    faker
    -0.09
     mob
    -0.09
    Lim
    -0.09
     Lim
    -0.09
     praise
    -0.09
     assessments
    -0.09
     bench
    -0.09
    POSITIVE LOGITS
     Knock
    0.17
     knocking
    0.17
     knock
    0.17
     knocks
    0.17
     caller
    0.17
     ringing
    0.16
     homeowner
    0.15
     knocked
    0.15
     hello
    0.15
     whoever
    0.14
    Activations Density 0.040%

    No Known Activations