© 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. 15525
    Prev
    Next
    INDEX
    Explanations

    trapped

    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
    Postal
    -0.11
     crisp
    -0.10
     leaps
    -0.10
     PRIV
    -0.10
    lage
    -0.10
     rejo
    -0.10
     brisk
    -0.10
    adir
    -0.10
     destabil
    -0.09
     carro
    -0.09
    POSITIVE LOGITS
     forever
    0.18
     Forever
    0.17
     unable
    0.16
    unable
    0.14
     indefinitely
    0.13
     inability
    0.12
     unwilling
    0.11
     trapped
    0.11
     Unable
    0.11
    esc
    0.11
    Activations Density 0.086%

    No Known Activations