© 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. 4452
    Prev
    Next
    INDEX
    Explanations

    girl or girls

    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
     tot
    -0.08
     haul
    -0.08
    isode
    -0.08
     groundwork
    -0.08
    CRT
    -0.07
     accrued
    -0.07
     flags
    -0.07
    .ContextCompat
    -0.07
     unb
    -0.07
    izzare
    -0.07
    POSITIVE LOGITS
     foc
    0.11
    /man
    0.10
     Jeans
    0.10
     Furn
    0.09
     Mime
    0.09
     standby
    0.09
    friend
    0.09
    @brief
    0.09
    .SuppressLint
    0.09
     Simmons
    0.09
    Activations Density 0.038%

    No Known Activations