© 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. 31324
    Prev
    Next
    INDEX
    Explanations

    starting quotes or sentence beginnings

    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
    IFn
    -0.13
     Klo
    -0.12
     Fucked
    -0.11
     WRITE
    -0.11
    OldData
    -0.11
    -remove
    -0.11
    efore
    -0.11
    unlink
    -0.10
     Pioneer
    -0.10
    ,U
    -0.10
    POSITIVE LOGITS
     How
    0.10
     how
    0.10
     a
    0.10
    ä¸Ģ个
    0.10
     An
    0.09
    How
    0.09
     an
    0.09
     impro
    0.08
    how
    0.08
     discovering
    0.08
    Activations Density 0.059%

    No Known Activations