© 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. 16282
    Prev
    Next
    INDEX
    Explanations

    password requirements

    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
     Morrow
    -0.10
     inspect
    -0.09
     warm
    -0.09
    leur
    -0.09
    about
    -0.09
    warm
    -0.09
    abouts
    -0.09
    /pop
    -0.08
     thorough
    -0.08
    elow
    -0.08
    POSITIVE LOGITS
    /pass
    0.17
     cracking
    0.12
     *****
    0.12
    -hash
    0.12
    /Login
    0.11
    =password
    0.11
    less
    0.11
     Strength
    0.11
    _strength
    0.11
     strength
    0.11
    Activations Density 0.032%

    No Known Activations