© 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. 16737
    Prev
    Next
    INDEX
    Explanations

    names starting with "Steve"

    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
     Leone
    -0.08
     Lehr
    -0.08
     slash
    -0.08
    iju
    -0.08
     SD
    -0.08
    utto
    -0.08
     schw
    -0.08
     vit
    -0.08
     refl
    -0.08
     Templ
    -0.08
    POSITIVE LOGITS
    bow
    0.10
    alus
    0.10
    /drivers
    0.09
     Validators
    0.09
    wards
    0.09
     thereafter
    0.09
    OID
    0.09
    addy
    0.09
    cid
    0.09
    hood
    0.09
    Activations Density 0.010%

    No Known Activations