© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52602
    Prev
    Next
    INDEX
    Explanations

    master prefixes

    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
    åĦ¿
    -0.09
    anged
    -0.09
    éĩİ
    -0.08
    åĩĢèµĦ产
    -0.08
    lj
    -0.08
    å°ıå¾®
    -0.08
    onaut
    -0.08
    è´
    -0.08
    éĻµ
    -0.08
    个
    -0.08
    POSITIVE LOGITS
    .Master
    0.13
    (master
    0.13
    /master
    0.12
    masters
    0.12
    master
    0.11
     masters
    0.11
     master
    0.11
     Master
    0.11
    .master
    0.11
     Masters
    0.10
    Activations Density 0.042%

    No Known Activations