© 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. 25444
    Prev
    Next
    INDEX
    Explanations

    password hashing or storage

    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
    eka
    -0.11
     Attribution
    -0.10
     anonymous
    -0.09
    -signed
    -0.09
     attribution
    -0.09
     buc
    -0.09
    anonymous
    -0.09
    PID
    -0.09
     whistle
    -0.09
     Hog
    -0.09
    POSITIVE LOGITS
     passwords
    0.23
     brute
    0.21
     Password
    0.20
     password
    0.20
    Passwords
    0.20
    password
    0.18
    Password
    0.18
    =password
    0.18
    .password
    0.18
     brut
    0.17
    Activations Density 0.607%

    No Known Activations