© 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. 14654
    Prev
    Next
    INDEX
    Explanations

    I'd/we'd like to hear

    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
    OSH
    -0.11
     telling
    -0.11
     Rao
    -0.11
     Lent
    -0.10
    achen
    -0.10
    ells
    -0.10
     Helping
    -0.10
    nown
    -0.09
     Pip
    -0.09
     Woj
    -0.09
    POSITIVE LOGITS
     welcomes
    0.24
     welcome
    0.24
     invites
    0.18
     invite
    0.16
     appreciate
    0.16
     Wel
    0.16
     welcoming
    0.16
     welcomed
    0.16
     hear
    0.15
     encourage
    0.15
    Activations Density 0.194%

    No Known Activations