© 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. 114180
    Prev
    Next
    INDEX
    Explanations

    leave followed by various words

    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
    rose
    -0.08
    orama
    -0.08
    ged
    -0.08
    imp
    -0.08
    west
    -0.08
    kl
    -0.08
    ons
    -0.08
     Paz
    -0.08
    ally
    -0.08
    (ed
    -0.08
    POSITIVE LOGITS
     Leave
    0.12
    eec
    0.12
     leave
    0.12
    hower
    0.11
    leave
    0.11
    .leave
    0.11
    mant
    0.11
     Chapman
    0.10
     mant
    0.10
     embr
    0.10
    Activations Density 0.008%

    No Known Activations