© 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. 32851
    Prev
    Next
    INDEX
    Explanations

    get

    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
     rid
    -0.12
    bish
    -0.11
    svp
    -0.10
    owe
    -0.10
     Ridley
    -0.09
    chl
    -0.09
     Klo
    -0.09
    hop
    -0.09
    CN
    -0.09
    inds
    -0.09
    POSITIVE LOGITS
    get
    0.11
     get
    0.11
    ym
    0.10
    (get
    0.10
     nib
    0.10
    gets
    0.09
    /get
    0.09
    ,get
    0.09
    Get
    0.09
     getting
    0.09
    Activations Density 0.931%

    No Known Activations