© 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. 113275
    Prev
    Next
    INDEX
    Explanations

    refuse or grant permission

    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
    bai
    -0.11
    prefs
    -0.11
    è°
    -0.11
     bait
    -0.10
     thanked
    -0.10
    ioc
    -0.10
     Schwartz
    -0.10
     Rice
    -0.10
     Summers
    -0.10
     praises
    -0.10
    POSITIVE LOGITS
     refuse
    0.24
     refused
    0.24
     granting
    0.22
     refusal
    0.22
     grant
    0.22
     granted
    0.22
     refuses
    0.21
     grants
    0.19
     refusing
    0.18
     Grant
    0.18
    Activations Density 0.141%

    No Known Activations