© 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. 4392
    Prev
    Next
    INDEX
    Explanations

    vai um

    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
    elia
    -0.08
    ady
    -0.08
     Dome
    -0.07
     smack
    -0.07
     astr
    -0.07
    Ñĥб
    -0.07
     Barth
    -0.07
     unemployed
    -0.07
     phẩm
    -0.07
    aps
    -0.07
    POSITIVE LOGITS
     revers
    0.13
    oux
    0.12
     lives
    0.12
    contents
    0.11
     reversing
    0.11
     invis
    0.10
    ÑıÑĤ
    0.10
     lived
    0.10
    elight
    0.10
    chw
    0.10
    Activations Density 0.021%

    No Known Activations