© 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. 90203
    Prev
    Next
    INDEX
    Explanations

    uns followed by words negative or lacking

    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
    upported
    -0.13
    pecified
    -0.12
    arse
    -0.11
    aret
    -0.10
     mental
    -0.10
     Mental
    -0.10
    assi
    -0.09
    azi
    -0.09
     Lesbian
    -0.09
    opts
    -0.09
    POSITIVE LOGITS
     uns
    0.25
     Uns
    0.23
    uns
    0.20
    ightly
    0.13
    peak
    0.13
     UNS
    0.11
    y
    0.11
    UNS
    0.11
    quam
    0.11
    rir
    0.10
    Activations Density 0.012%

    No Known Activations