© 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. 31249
    Prev
    Next
    INDEX
    Explanations

    username and password

    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
    oller
    -0.09
    /manual
    -0.09
    /use
    -0.09
    mans
    -0.09
    ilion
    -0.08
    inder
    -0.08
    renc
    -0.08
     Unified
    -0.08
    ValueChanged
    -0.08
    iver
    -0.08
    POSITIVE LOGITS
    AndPassword
    0.14
    /password
    0.11
    /email
    0.10
     vice
    0.10
    akan
    0.09
    vfs
    0.09
    fld
    0.09
    /filepath
    0.09
    hausen
    0.09
    riad
    0.09
    Activations Density 0.039%

    No Known Activations