© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8793
    Prev
    Next
    INDEX
    Explanations

    authentication, thousands, http

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    SSION
    -0.13
    ities
    -0.13
    ETCH
    -0.11
    eut
    -0.11
    ULAR
    -0.10
    ision
    -0.10
    ções
    -0.10
    hev
    -0.10
    keit
    -0.10
    erate
    -0.10
    POSITIVE LOGITS
    entication
    0.15
    enticated
    0.14
    enticate
    0.14
    enticator
    0.14
    ened
    0.14
    ousand
    0.13
    ttp
    0.13
    ening
    0.12
    rea
    0.12
    ousands
    0.11
    Activations Density 0.260%

    No Known Activations