© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58057
    Prev
    Next
    INDEX
    Explanations

    Samoa and governor"}

    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
    iera
    -0.10
    ×ķ×Ļ×ķת
    -0.09
    éķ¿çŁŃ
    -0.09
    emption
    -0.09
    кеÑĢ
    -0.08
    笼
    -0.08
    isque
    -0.08
    çī¢åĽº
    -0.08
    ocop
    -0.08
    åĨµ
    -0.08
    POSITIVE LOGITS
    没åħ³ç³»
    0.11
    nim
    0.10
    éľĸ
    0.09
    çĨŁ
    0.09
    çłĶ究çĶŁ
    0.08
    antar
    0.08
    èıĩ
    0.08
     improv
    0.08
     Skinner
    0.08
    èĩ»
    0.08
    Activations Density 0.046%

    No Known Activations