© 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. 27786
    Prev
    Next
    INDEX
    Explanations

    legal and positional 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
    Not in Any Lists

    No Comments

    Negative Logits
     unab
    -0.10
     unrestricted
    -0.09
     breadcrumbs
    -0.08
     unprotected
    -0.08
     consciously
    -0.08
     precaution
    -0.08
     Pang
    -0.07
     nud
    -0.07
     accessible
    -0.07
     stamp
    -0.07
    POSITIVE LOGITS
     nobody
    0.23
     Nobody
    0.21
    Nobody
    0.18
     obscured
    0.15
     obs
    0.15
    idak
    0.14
     obscure
    0.14
     dim
    0.13
     mirac
    0.13
     opaque
    0.13
    Activations Density 0.036%

    No Known Activations