© 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. 31081
    Prev
    Next
    INDEX
    Explanations

    refused to leave

    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
     Narrow
    -0.10
     Conj
    -0.09
    243
    -0.09
     Ridge
    -0.09
     prem
    -0.09
    ÃĤ
    -0.09
    multiline
    -0.09
    -ce
    -0.08
     nab
    -0.08
     Conte
    -0.08
    POSITIVE LOGITS
     refusal
    0.11
     Kami
    0.09
     refused
    0.09
     refusing
    0.09
    ISTA
    0.09
     beforehand
    0.09
     laisse
    0.09
     soc
    0.09
    esch
    0.09
    variably
    0.09
    Activations Density 0.025%

    No Known Activations