© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117396
    Prev
    Next
    INDEX
    Explanations

    knock phrases

    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
    Negative Logits
     lif
    -0.12
     oath
    -0.10
    rary
    -0.10
    ldr
    -0.10
    Dims
    -0.10
    gam
    -0.10
     UserController
    -0.10
     Shr
    -0.10
     McMaster
    -0.10
    ÑĥÑī
    -0.10
    POSITIVE LOGITS
     Knock
    0.13
     knock
    0.13
     knocked
    0.10
     knocking
    0.10
     knocks
    0.09
    Kn
    0.09
     unconscious
    0.08
     hustle
    0.08
     socks
    0.08
     banged
    0.08
    Activations Density 0.013%

    No Known Activations