© 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. 29195
    Prev
    Next
    INDEX
    Explanations

    以 and åı¯

    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
    ivr
    -0.13
    parm
    -0.12
    kil
    -0.12
    ogr
    -0.11
     NU
    -0.11
    pez
    -0.11
     utmost
    -0.11
    ilos
    -0.11
    .initState
    -0.11
     Mai
    -0.11
    POSITIVE LOGITS
    åĥı
    0.09
     member
    0.08
    olarity
    0.08
     in
    0.08
     appearing
    0.07
     Zam
    0.07
    è¢
    0.07
     Plat
    0.07
     Lite
    0.07
    ^-
    0.07
    Activations Density 0.017%

    No Known Activations