© 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. 88790
    Prev
    Next
    INDEX
    Explanations

    help and its consequences

    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
     Helping
    -0.11
    otor
    -0.10
     Help
    -0.09
     happily
    -0.09
     helping
    -0.09
    anon
    -0.09
     Zu
    -0.09
     pag
    -0.09
    cest
    -0.09
    asher
    -0.09
    POSITIVE LOGITS
     immensely
    0.23
     tremendously
    0.21
     enormously
    0.19
     greatly
    0.15
     considerably
    0.15
     us
    0.13
     tremend
    0.13
     matters
    0.13
     significantly
    0.12
     to
    0.12
    Activations Density 0.048%

    No Known Activations