© 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. 50555
    Prev
    Next
    INDEX
    Explanations

    dangerous precedent or slippery slope

    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
    zb
    -0.10
    ega
    -0.09
     simultaneous
    -0.09
     roughly
    -0.09
    wit
    -0.08
     Isa
    -0.08
    422
    -0.08
    ersist
    -0.08
    .lift
    -0.08
    nett
    -0.08
    POSITIVE LOGITS
     precedent
    0.38
     slippery
    0.37
     preced
    0.29
     Pandora
    0.26
     Slip
    0.25
    preced
    0.23
     precedence
    0.23
     opened
    0.20
     opening
    0.20
     pave
    0.19
    Activations Density 0.162%

    No Known Activations