© 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. 114088
    Prev
    Next
    INDEX
    Explanations

    fullness

    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
     ferv
    -0.11
     Deg
    -0.10
     shr
    -0.09
     consenting
    -0.09
     unlocked
    -0.09
     Hosp
    -0.09
     tac
    -0.09
     consent
    -0.09
     inject
    -0.08
     stud
    -0.08
    POSITIVE LOGITS
     filling
    0.33
     fills
    0.30
     fill
    0.28
    fill
    0.28
     Fill
    0.25
    å¡«
    0.25
    fills
    0.23
    Fill
    0.23
    -fill
    0.23
     filled
    0.22
    Activations Density 0.043%

    No Known Activations