© 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. 116675
    Prev
    Next
    INDEX
    Explanations

    you will

    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
     your
    -0.09
    flo
    -0.08
     entr
    -0.08
    allo
    -0.08
     should
    -0.08
     chill
    -0.07
    sp
    -0.07
     Sp
    -0.07
     penetr
    -0.07
     Your
    -0.06
    POSITIVE LOGITS
     normally
    0.13
    normally
    0.12
    idth
    0.12
     ordinarily
    0.12
     Promise
    0.12
    ahu
    0.12
     hate
    0.12
     promise
    0.12
    ãģĤãĤĬãģĮ
    0.11
     Normally
    0.11
    Activations Density 0.027%

    No Known Activations