© 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. 38207
    Prev
    Next
    INDEX
    Explanations

    Such [noun/concept]

    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
    主è¦ģåĨħ容
    -0.09
    缸åħ³æĶ¿çŃĸ
    -0.09
    æĬ¢éĻ©
    -0.08
    ราà¸ĩ
    -0.08
    /or
    -0.08
    usz
    -0.08
    æīĢæıIJä¾Ľ
    -0.08
    åĨ¤
    -0.08
    èĥľè´Ł
    -0.08
    çħ®
    -0.08
    POSITIVE LOGITS
    oop
    0.10
    zelf
    0.09
    leet
    0.09
    æĺİ
    0.09
     Ñģебе
    0.08
     воÑĤ
    0.08
    å¾Ģ
    0.08
    ors
    0.08
    onest
    0.08
    iance
    0.08
    Activations Density 0.040%

    No Known Activations