© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    declines or insists

    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
     ful
    -0.10
    utr
    -0.10
     Devon
    -0.10
    /il
    -0.10
    ardin
    -0.10
     fulfil
    -0.10
     dumped
    -0.09
     bored
    -0.09
    @if
    -0.09
     Amen
    -0.09
    POSITIVE LOGITS
     insisted
    0.20
     declined
    0.19
     insistence
    0.18
     insists
    0.18
     insist
    0.18
     declines
    0.17
     insisting
    0.17
     rejected
    0.16
     refusal
    0.16
     decline
    0.15
    Activations Density 0.042%

    No Known Activations