© 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. 14953
    Prev
    Next
    INDEX
    Explanations

    Pan American

    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
    i
    -0.10
     Alt
    -0.10
    shal
    -0.09
    Alt
    -0.09
    odate
    -0.08
    brown
    -0.08
    ables
    -0.08
    yu
    -0.08
     intrinsic
    -0.08
     Bite
    -0.08
    POSITIVE LOGITS
    icking
    0.13
    acea
    0.13
    theon
    0.10
    athlon
    0.10
    icos
    0.10
    uju
    0.10
    icked
    0.10
    cho
    0.10
     UNIVERS
    0.10
    continental
    0.10
    Activations Density 0.010%

    No Known Activations